© 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

    random.randint calls (negative activations)

    python-code · gemini-2.5-flash-lite

    tuple assignment or unpacking

    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
    .position
    -0.06
    _coords
    -0.04
    udoku
    -0.04
     sele
    -0.04
    _position
    -0.04
     positions
    -0.04
     [-
    -0.03
    _loc
    -0.03
    oal
    -0.03
    Positive Logits
    uel
    0.06
    _cost
    0.05
    value
    0.05
     cost
    0.04
     I
    0.04
     lat
    0.04
    rice
    0.04
    riority
    0.03
    .values
    0.03
     val
    0.03
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string type or literal (negative activations)

    python-code · gemini-2.5-flash-lite

    division assignment

    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
    .add
    -0.03
    },↵
    -0.03
    ė
    -0.02
    .index
    -0.02
    ē
    -0.02
    |>
    -0.02
    .get
    -0.02
    .read
    -0.02
    .remove
    -0.02
     True
    -0.02
    Positive Logits
    jkstra
    0.03
    ~
    0.03
    %
    0.02
    udoku
    0.02
     ob
    0.02
    Ä
    0.01
     (
    0.01
    uc
    0.01
     o
    0.01
     j
    0.01
    Activations Density 98.164%

    No Known Activations