© 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. 2353
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    argument in a method call (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment statement for attribute

    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
     c
    -0.02
    _c
    -0.02
    0
    -0.01
     given
    -0.01
    cle
    -0.01
    cy
    -0.01
    zero
    -0.01
    (c
    -0.01
     spe
    -0.01
    .c
    -0.01
    POSITIVE LOGITS
    ,↵
    0.01
     <=
    0.01
     {↵
    0.01
    ound
    0.01
    ,
    0.01
    ][
    0.01
    .txt
    0.01
     any
    0.01
    ],
    0.01
    .is
    0.00
    Activations Density 96.936%

    No Known Activations