© 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

    plural attribute names ending in s

    python-code · gemini-2.5-flash-lite

    opening parenthesis of a print statement (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
     top
    -0.05
    þ
    -0.04
    ü
    -0.04
    ö
    -0.04
    À
    -0.04
    <invalid_2046>
    -0.04
    ÷
    -0.04
    ù
    -0.04
    ý
    -0.04
    õ
    -0.04
    Positive Logits
    ry
    0.05
    reshold
    0.04
    con
    0.03
    iti
    0.03
    ateg
    0.03
    ange
    0.03
    en
    0.03
    ary
    0.03
    ool
    0.03
    ents
    0.03
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations
    No Explanations Found
    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
     representing
    -0.11
     that
    -0.07
     given
    -0.07
    ip
    -0.07
     each
    -0.07
     the
    -0.07
    ]][
    -0.06
     represe
    -0.06
    _rate
    -0.06
     based
    -0.05
    Positive Logits
    ð
    0.11
    :↵
    0.05
    losest
    0.05
     else
    0.05
    ne
    0.04
     sys
    0.04
    s
    0.04
    da
    0.04
     ne
    0.04
    ice
    0.04
    Activations Density 77.279%

    No Known Activations