© 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. 7011
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    max function argument (negative activations)

    python-code · gemini-2.5-flash-lite

    function argument or call parenthesis

    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
     dp
    -0.06
     form
    -0.06
    _file
    -0.05
    ilename
    -0.04
     file
    -0.04
     optim
    -0.04
     results
    -0.04
    udoku
    -0.04
    ilen
    -0.03
     dfs
    -0.03
    POSITIVE LOGITS
    fset
    0.07
    hor
    0.05
     directions
    0.05
    visited
    0.05
     neighbors
    0.05
     visited
    0.05
     moves
    0.04
    isited
    0.04
    _neighbors
    0.04
     dx
    0.04
    Activations Density 99.999%

    No Known Activations