© 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

    exception handling blocks

    python-code · gemini-2.5-flash-lite

    variable named `d` (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
     P
    -0.02
    P
    -0.02
    ...
    -0.01
    p
    -0.01
    _capacity
    -0.01
     car
    -0.01
    .c
    -0.01
    _c
    -0.01
     cities
    -0.01
     closest
    -0.01
    Positive Logits
    _to
    0.05
    _from
    0.04
     to
    0.04
     from
    0.04
    rom
    0.03
     e
    0.03
    from
    0.03
     ->
    0.02
     cost
    0.01
     between
    0.01
    Activations Density 99.995%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function call `(` or empty tuple `()`

    python-code · gemini-2.5-flash-lite

    list index 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
    #
    -0.09
     #
    -0.09
     Testing
    -0.08
     Test
    -0.07
    endoftext
    -0.07
    |>
    -0.06
    ↵        ↵
    -0.06
    ↵
    -0.06
    .in
    -0.05
    ↵↵
    -0.05
    Positive Logits
    (list
    0.07
    list
    0.06
    List
    0.06
     List
    0.06
     list
    0.05
    ted
    0.05
    _i
    0.05
    :↵
    0.05
    _list
    0.05
    gth
    0.05
    Activations Density 100.000%

    No Known Activations