© 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

    conditional statement 'if' (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
    age
    -0.11
     \
    -0.10
    ars
    -0.10
    arch
    -0.08
    ar
    -0.08
    array
    -0.08
     other
    -0.07
    _idx
    -0.07
    ariables
    -0.06
    55
    -0.06
    Positive Logits
     dictionary
    0.22
    dict
    0.20
     dict
    0.16
    .values
    0.16
    ctionary
    0.16
    _dict
    0.14
    .keys
    0.14
    .items
    0.13
    reshold
    0.12
    apping
    0.12
    Activations Density 99.909%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dict assignment or key access (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
     P
    -0.02
    P
    -0.02
     not
    -0.02
    p
    -0.01
    ast
    -0.01
    q
    -0.01
    rans
    -0.00
    code
    -0.00
    0
    0.00
    3
    0.00
    Positive Logits
    +
    0.03
    -
    0.03
    %
    0.03
    {
    0.03
    *
    0.02
    @
    0.02
    &
    0.02
    #
    0.02
    /
    0.02
    =
    0.02
    Activations Density 85.543%

    No Known Activations