© 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

    closing brace or bracket

    python-code · gemini-2.5-flash-lite

    function argument definition (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
    -0.04
    .m
    -0.04
    ag
    -0.02
    ip
    -0.02
     second
    -0.02
    lf
    -0.02
    he
    -0.01
    arch
    -0.01
     sorted
    -0.01
    ser
    -0.01
    Positive Logits
    uzzle
    0.04
    udok
    0.04
    mpty
    0.04
     nx
    0.04
    uzz
    0.04
    ry
    0.04
    ities
    0.03
    ity
    0.03
    _valid
    0.03
     solve
    0.03
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment uses equals

    python-code · gemini-2.5-flash-lite

    list element 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
    uristic
    -0.08
    el
    -0.06
    lable
    -0.06
    oal
    -0.06
    struction
    -0.05
    istic
    -0.05
    rontier
    -0.05
     goal
    -0.05
    mory
    -0.05
    p
    -0.05
    Positive Logits
    ul
    0.09
    own
    0.09
     '#
    0.08
    up
    0.08
     lat
    0.08
     cur
    0.08
     continue
    0.07
    uples
    0.07
     ('
    0.07
     (-
    0.07
    Activations Density 100.000%

    No Known Activations