© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2811
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis for function calls (negative activations)

    python-code · gemini-2.5-flash-lite

    class initialization

    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
     dfs
    -0.06
    gorithm
    -0.05
     dp
    -0.04
     algorithm
    -0.04
    idth
    -0.04
    jkstra
    -0.04
     solve
    -0.04
     count
    -0.04
    _len
    -0.03
    heck
    -0.03
    POSITIVE LOGITS
     form
    0.06
    _from
    0.04
     en
    0.03
     to
    0.03
     input
    0.03
    _to
    0.03
     between
    0.02
     from
    0.02
     us
    0.02
    (input
    0.02
    Activations Density 99.976%

    No Known Activations