© 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 or dictionary assignment (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
    pected
    -0.09
    uild
    -0.08
     base
    -0.07
    uil
    -0.06
     build
    -0.06
    unc
    -0.05
    rack
    -0.05
    _un
    -0.05
    unction
    -0.05
    Į
    -0.05
    Positive Logits
    ()
    0.04
    ,↵
    0.03
    ',↵
    0.02
     },↵
    0.02
     [↵
    0.02
     """↵
    0.02
     >
    0.02
    ",↵
    0.02
    },↵
    0.02
     {↵
    0.02
    Activations Density 89.165%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment after 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
    turn
    -0.06
    ctionary
    -0.05
    dividual
    -0.05
    <
    -0.05
    dices
    -0.04
    maining
    -0.04
    ;
    -0.04
    stance
    -0.04
    duct
    -0.04
    splay
    -0.04
    Positive Logits
    oard
    0.10
    aze
    0.09
    grid
    0.09
    _grid
    0.09
     grid
    0.09
     graph
    0.09
    udoku
    0.08
     maze
    0.08
    .grid
    0.08
     board
    0.08
    Activations Density 94.862%

    No Known Activations