© 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

    numbers and the keyword `if`

    python-code · gemini-2.5-flash-lite

    with open (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
     lat
    -0.11
    itude
    -0.10
    lat
    -0.09
     break
    -0.07
    ge
    -0.07
    udoku
    -0.07
    uzzle
    -0.06
    gest
    -0.06
    udok
    -0.06
    ash
    -0.06
    Positive Logits
     __
    0.16
    __(
    0.16
    __
    0.14
    __':↵
    0.11
     "__
    0.10
    __":↵
    0.09
     other
    0.09
    Ñ
    0.09
    Ð
    0.08
    other
    0.07
    Activations Density 67.255%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable 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
    ink
    -0.05
    de
    -0.04
    _de
    -0.03
    .de
    -0.03
    t
    -0.03
    \
    -0.03
    (de
    -0.03
     dest
    -0.03
    .t
    -0.02
    ().
    -0.02
    Positive Logits
    qui
    0.07
    end
    0.04
    zero
    0.04
     end
    0.04
    (s
    0.04
     file
    0.04
    dex
    0.03
    ul
    0.02
    dict
    0.02
    s
    0.01
    Activations Density 61.443%

    No Known Activations