---
title: Interpretability
description: 'The degree to which a human can understand how a model represents information or produces behavior.'
canonical_url: 'https://darkfactory.dev/glossary/interpretability'
markdown_url: 'https://darkfactory.dev/glossary/interpretability.md'
collection: glossary
date_published: '2026-08-03T00:00:00-04:00'
date_modified: '2026-08-26T00:00:00-04:00'
---

# Interpretability


## Definition

Interpretability is the degree to which a person can understand how a model represents information or produces behavior. The target might be a single prediction, the role of a feature, a learned concept, a circuit inside a neural network, or the model's behavior across an entire class of inputs.

An interpretation should make a claim that can be tested. Feature attribution, probes, activation analysis, causal interventions, and simpler surrogate models offer different evidence and carry different limits. A visualization that looks meaningful is not enough if changing the alleged mechanism does not change the behavior.

## Distinguish it from nearby terms

Explainability usually concerns a human-usable account for an output or action. Interpretability can go deeper into the model's underlying representations and mechanisms. Post-hoc explanations may approximate behavior without showing what the original model actually used.

## Check your understanding

A probe can predict whether an internal activation encodes sentiment. That shows the information is available there, not that the model uses it to choose the answer. A stronger interpretation would test the causal link.

## Related terms

- [Explainability](https://darkfactory.dev/glossary/explainability)
- [Post-hoc explanation](https://darkfactory.dev/glossary/post-hoc-explanation)

## Evidence and further reading

- [NIST AI Resource Center Glossary](https://airc.nist.gov/glossary/)
- [Google Machine Learning Glossary](https://developers.google.com/machine-learning/glossary/)