Neuronpedia

Evals

Tool (not an eval — tooling/reference entry)

Open interpretability platform (features, circuits, steering).

Category
Model-internals auditing
Insurance exposure
Model failure
Publisher
Neuronpedia
Publisher type
Nonprofit / research org
License
Apache-2.0
Status
Active (<90d)
Last commit
2026-10-15
Stars
1169

View source on GitHub →

Wanich Risk Lab, 2026.