© 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. 2603
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    for loop constructs (negative activations)

    python-code · gemini-2.5-flash-lite

    function call arguments

    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
     function
    -0.07
     algorithm
    -0.07
     Find
    -0.05
    .find
    -0.04
     dfs
    -0.04
    =None
    -0.04
     find
    -0.04
     between
    -0.04
    ='
    -0.03
    thod
    -0.03
    POSITIVE LOGITS
    over
    0.03
     dp
    0.03
     found
    0.03
    _move
    0.02
     based
    0.02
    _comb
    0.02
    _rate
    0.02
    mple
    0.02
    init
    0.02
    _counts
    0.01
    Activations Density 97.792%

    No Known Activations