© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string method startswith

    python-code · gemini-2.5-flash-lite

    function definition keyword (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    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
    Negative Logits
     \
    -0.03
    The
    -0.03
    iven
    -0.03
     the
    -0.02
     The
    -0.02
     This
    -0.02
    qui
    -0.02
     each
    -0.01
    his
    -0.01
     Return
    -0.01
    Positive Logits
    reshold
    0.04
    vai
    0.03
    uel
    0.03
    endoftext
    0.03
     {
    0.03
     %
    0.03
    _scores
    0.03
    self
    0.02
    vailable
    0.02
    itude
    0.02
    Activations Density 90.516%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    for loop iteration variable

    python-code · gemini-2.5-flash-lite

    return followed by an expression (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    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
    Negative Logits
     Calculate
    -0.04
    ns
    -0.03
    etween
    -0.03
    _tra
    -0.03
     abs
    -0.02
    ta
    -0.02
     graph
    -0.02
     math
    -0.02
     tra
    -0.02
     map
    -0.02
    Positive Logits
    .position
    0.07
     found
    0.04
    _coords
    0.04
    _position
    0.04
     positions
    0.04
     while
    0.04
    _loc
    0.03
     coordinates
    0.03
    es
    0.03
                       
    0.03
    Activations Density 98.179%

    No Known Activations