© 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 literal comma separator

    python-code · gemini-2.5-flash-lite

    list initialization values (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
     un
    -0.12
     qu
    -0.06
    _v
    -0.06
     con
    -0.05
     [
    -0.05
     ve
    -0.05
    (w
    -0.05
            ↵
    -0.04
     //
    -0.04
    (v
    -0.04
    Positive Logits
    ilities
    0.13
    out
    0.12
    tic
    0.12
    ized
    0.10
    ility
    0.10
    ize
    0.08
    iz
    0.07
    xF
    0.06
    ariable
    0.06
    tive
    0.06
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    maketrans call and transactions

    python-code · gemini-2.5-flash-lite

    list item separator or 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
    opulation
    -0.11
    _population
    -0.09
     population
    -0.09
    itness
    -0.08
    xF
    -0.08
    dividual
    -0.07
     ==
    -0.06
    term
    -0.04
    į
    -0.04
    loat
    -0.04
    Positive Logits
     nx
    0.07
     ny
    0.06
    ili
    0.04
    ()<|
    0.04
    )<|
    0.04
    osition
    0.04
    .position
    0.04
    ility
    0.04
    ket
    0.04
    action
    0.04
    Activations Density 100.000%

    No Known Activations