© 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

    instance of list or str (negative activations)

    python-code · gemini-2.5-flash-lite

    variable names in assignment

    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
    lambda
    -0.03
    (str
    -0.03
    ver
    -0.02
    (int
    -0.02
     a
    -0.01
     _
    -0.01
     (
    -0.01
    ((
    -0.01
     nodes
    -0.00
    '
    0.00
    Positive Logits
    ight
    0.02
     di
    0.02
       
    0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    !
    0.00
    Activations Density 31.658%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comma separating arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    closing parenthesis or comma in list/tuple

    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
    (line
    -0.03
    _with
    -0.03
    ith
    -0.03
     whe
    -0.03
     ->
    -0.03
    mmand
    -0.03
    ty
    -0.02
     test
    -0.02
     with
    -0.02
     that
    -0.02
    Positive Logits
    (ro
    0.03
    ameters
    0.02
    (pro
    0.02
    am
    0.02
    ch
    0.02
     /
    0.02
     shortest
    0.01
    uple
    0.01
    us
    0.01
    ames
    0.01
    Activations Density 70.571%

    No Known Activations