© 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

    list indices or slicing (negative activations)

    python-code · gemini-2.5-flash-lite

    self attribute initialization

    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
    etween
    -0.03
     abs
    -0.03
    ta
    -0.02
     math
    -0.02
     -
    -0.02
    gle
    -0.01
    -
    -0.01
     [-
    -0.01
    (point
    -0.01
    Positive Logits
     name
    0.03
    ames
    0.03
    name
    0.02
    .name
    0.02
    _name
    0.02
    .add
    0.02
    ame
    0.01
    add
    0.01
     best
    0.00
    new
    0.00
    Activations Density 32.421%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to variable `b` (negative activations)

    python-code · gemini-2.5-flash-lite

    operator.itemgetter

    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
    alse
    -0.06
    rue
    -0.06
    sen
    -0.05
    False
    -0.05
    True
    -0.04
    .parent
    -0.04
     True
    -0.04
     False
    -0.04
    ush
    -0.04
     heapq
    -0.04
    Positive Logits
     get
    0.04
    get
    0.04
    .get
    0.03
    join
    0.02
    ","
    0.02
     else
    0.02
    lable
    0.02
    ",
    0.02
    ',
    0.02
     min
    0.01
    Activations Density 74.516%

    No Known Activations