© 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

    dot (`.`) followed by a method name (negative activations)

    python-code · gemini-2.5-flash-lite

    dictionary .get method

    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
    heck
    -0.03
     True
    -0.03
    is
    -0.03
     check
    -0.03
    .find
    -0.02
     Check
    -0.02
    are
    -0.02
    .is
    -0.02
     has
    -0.02
     find
    -0.02
    Positive Logits
    qrt
    0.07
     break
    0.04
    rior
    0.03
    lose
    0.03
    uration
    0.02
     the
    0.02
    ies
    0.02
     found
    0.02
    alue
    0.02
     str
    0.02
    Activations Density 99.919%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis in function 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
    ty
    -0.07
    ob
    -0.04
    ]
    -0.04
     the
    -0.03
    (len
    -0.02
    .txt
    -0.02
    .values
    -0.02
    [str
    -0.02
                ↵
    -0.02
    [int
    -0.02
    Positive Logits
     or
    0.07
    type
    0.05
     and
    0.04
     for
    0.04
     +
    0.03
    .is
    0.03
     [
    0.03
    _op
    0.02
    .num
    0.02
     *
    0.02
    Activations Density 24.333%

    No Known Activations