© 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

    variable assignment (negative activations)

    python-code · gemini-2.5-flash-lite

    function call or definition 'a'

    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
     given
    -0.03
     between
    -0.03
    fset
    -0.03
     based
    -0.03
     "
    -0.02
     from
    -0.02
     possible
    -0.02
    hor
    -0.02
     us
    -0.02
     directions
    -0.02
    Positive Logits
    mport
    0.07
    erge
    0.06
     update
    0.04
    his
    0.04
    mo
    0.04
    update
    0.03
     form
    0.02
     None
    0.02
     check
    0.02
    None
    0.02
    Activations Density 78.562%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    self.attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    instance method calls

    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
     generate
    -0.02
     int
    -0.01
    (n
    -0.01
    [n
    -0.01
    (N
    -0.01
    (num
    -0.01
    .p
    -0.00
    ')
    -0.00
     random
    -0.00
    om
    -0.00
    Positive Logits
    append
    0.05
    .remove
    0.04
    lose
    0.04
    ush
    0.03
    rior
    0.03
    .add
    0.03
    uration
    0.03
     set
    0.02
    ies
    0.02
     add
    0.02
    Activations Density 83.170%

    No Known Activations