© 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

    function definition followed by print (negative activations)

    python-code · gemini-2.5-flash-lite

    accessor for sorting

    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
    (N
    -0.03
    ake
    -0.03
    R
    -0.03
    E
    -0.03
    O
    -0.03
    V
    -0.03
    F
    -0.03
    C
    -0.03
    J
    -0.03
    P
    -0.03
    Positive Logits
     us
    0.03
     between
    0.03
     based
    0.02
     from
    0.02
     on
    0.02
     by
    0.02
    atus
    0.02
     that
    0.02
    _from
    0.02
    _by
    0.02
    Activations Density 90.448%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    range and function calls (negative activations)

    python-code · gemini-2.5-flash-lite

    not len

    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
    visited
    -0.04
     visited
    -0.04
    isited
    -0.03
    rontier
    -0.03
    123
    -0.02
    .name
    -0.02
    .id
    -0.02
    .add
    -0.02
     ele
    -0.02
     dfs
    -0.02
    Positive Logits
     not
    0.04
    No
    0.03
    anage
    0.03
    olver
    0.03
    uil
    0.02
     !=
    0.02
    Error
    0.02
    ator
    0.02
    lse
    0.02
     no
    0.02
    Activations Density 79.696%

    No Known Activations