© 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

    method call then list indexing

    python-code · gemini-2.5-flash-lite

    list element indexing (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
    (N
    -0.04
     defaultdict
    -0.03
    _height
    -0.02
    09
    -0.02
    _distance
    -0.02
    _w
    -0.02
    ser
    -0.02
     route
    -0.02
    _pro
    -0.02
     dp
    -0.02
    Positive Logits
    div
    0.05
    um
    0.04
    ld
    0.04
     >=
    0.04
     <=
    0.04
    [-
    0.04
     !=
    0.04
    }")↵↵
    0.04
    }")<|
    0.04
    _name
    0.04
    Activations Density 99.999%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `ax` or `mployee` in variable names

    python-code · gemini-2.5-flash-lite

    `random` module functions (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
    xF
    -0.06
    gest
    -0.05
    ses
    -0.05
    udent
    -0.05
    utation
    -0.05
     Calculate
    -0.05
    _id
    -0.05
    tity
    -0.05
    ):
    -0.04
    _number
    -0.04
    Positive Logits
    graph
    0.07
     Testing
    0.06
     else
    0.06
    ory
    0.05
    test
    0.05
     Test
    0.05
     test
    0.05
    _loc
    0.04
    _location
    0.04
     locations
    0.04
    Activations Density 100.000%

    No Known Activations