© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 6861
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literals in lists or tuples (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment to attribute variable

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :",
    -0.04
    :
    -0.03
    :-
    -0.03
     :
    -0.03
    ]['
    -0.02
    ][
    -0.02
    ):
    -0.02
    |
    -0.02
     Par
    -0.02
    ..
    -0.02
    POSITIVE LOGITS
     =
    0.04
    .append
    0.02
     not
    0.02
    .name
    0.02
    .id
    0.02
    _idx
    0.02
    ")↵
    0.02
    ")↵↵
    0.02
    dex
    0.02
    ')↵
    0.02
    Activations Density 45.338%

    No Known Activations