© 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
    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
     instruction
    -0.08
    udok
    -0.08
     instructions
    -0.07
    struction
    -0.07
    lauses
    -0.07
    dom
    -0.07
    structions
    -0.06
    udoku
    -0.06
    lause
    -0.06
    gram
    -0.06
    Positive Logits
    join
    0.10
    [str
    0.08
    split
    0.06
    _string
    0.05
    :-
    0.05
    _str
    0.05
    lable
    0.05
    ise
    0.04
    ses
    0.04
     optimal
    0.04
    Activations Density 95.938%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    end of list indexing

    python-code · gemini-2.5-flash-lite

    reverse slice notation [:-1] (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
    &
    0.00
    *
    0.00
    #
    0.00
    '
    0.00
    )
    0.00
    %
    0.00
    !
    0.00
    "
    0.00
    $
    0.00
    (
    0.00
    Positive Logits
    .add
    0.03
    ė
    0.03
    .index
    0.02
    ē
    0.02
    |>
    0.02
    .get
    0.02
    .read
    0.02
    .remove
    0.02
    True
    0.02
    .nodes
    0.02
    Activations Density 100.000%

    No Known Activations