A research library for mechanistic interpretability and Theory of Mind in large language models
-
Updated
Aug 31, 2026 - Python
#
mechanisticinterpretability
Here are 2 public repositories matching this topic...
Realtime unit labeling and debugging demo: streaming NeuronCards with confidence, stable identity under drift, and active probing for AI interpretability.
python debugging observability interpretability probing activelearning streamlit mechanisticinterpretability neuronlabeling featureattribution
-
Updated
Dec 17, 2025
Add this topic to your repo
To associate your repository with the mechanisticinterpretability topic, visit your repo's landing page and select "manage topics."