© 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

    indent argument for json.dumps

    python-code · gemini-2.5-flash-lite

    keyword `return` or `else` (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
    py
    -0.05
    neighbor
    -0.02
     whe
    -0.01
    us
    -0.01
     step
    -0.01
    of
    -0.01
     pro
    -0.01
    is
    -0.01
    _in
    -0.01
    he
    -0.01
    Positive Logits
    ases
    0.06
    ase
    0.06
    alue
    0.05
    roup
    0.05
    ariable
    0.05
    rice
    0.05
    ariables
    0.05
    Ô
    0.04
    Æ
    0.04
    udok
    0.04
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function or method definition (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
    ats
    -0.17
    at
    -0.15
    bs
    -0.15
    b
    -0.13
    ating
    -0.13
    ´
    -0.12
    arch
    -0.12
    ater
    -0.11
    ber
    -0.11
    att
    -0.11
    Positive Logits
     Graph
    0.16
    de
    0.14
    isi
    0.13
    raph
    0.11
    etwork
    0.11
    ram
    0.10
    ld
    0.10
    th
    0.10
    graph
    0.10
    arg
    0.10
    Activations Density 98.689%

    No Known Activations