© 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

    comparison and arithmetic operators

    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
    79
    -0.04
    75
    -0.04
    99
    -0.04
    70
    -0.04
    37
    -0.04
    66
    -0.04
    68
    -0.03
    15
    -0.03
    25
    -0.03
    35
    -0.03
    Positive Logits
    as
    0.04
     representing
    0.03
    udoku
    0.02
     that
    0.02
     given
    0.02
    g
    0.02
    st
    0.02
     total
    0.02
     each
    0.02
    l
    0.02
    Activations Density 9.802%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `.append`

    python-code · gemini-2.5-flash-lite

    `(` or variable names followed by `(` (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
     result
    -0.03
     Testing
    -0.03
     typing
    -0.03
    xF
    -0.02
     nx
    -0.02
    62
    -0.02
    77
    -0.02
    63
    -0.02
    76
    -0.02
     Test
    -0.02
    Positive Logits
    .remove
    0.04
    alculate
    0.03
    enerate
    0.03
     calculate
    0.03
     find
    0.03
     parse
    0.03
     create
    0.02
     Calculate
    0.02
    ulate
    0.02
     Find
    0.02
    Activations Density 23.976%

    No Known Activations