© 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. 2-MLP
    11. 5633
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing bracket of list item

    python-code · gemini-2.5-flash-lite

    assignment operator in python (negative activations)

    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
    -0.03
    ype
    -0.03
    rue
    -0.03
    st
    -0.03
    p
    -0.03
    en
    -0.03
    lat
    -0.03
    _mo
    -0.03
    D
    -0.03
     operation
    -0.02
    POSITIVE LOGITS
     [↵
    0.06
    action
    0.04
    ,↵
    0.04
    ;
    0.04
     action
    0.04
    thod
    0.04
    ',↵
    0.03
    actions
    0.03
    re
    0.03
     },↵
    0.03
    Activations Density 100.000%

    No Known Activations