© 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

    string join method (negative activations)

    python-code · gemini-2.5-flash-lite

    turtle.pendown or turtle.delete

    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
    ain
    -0.04
    reshold
    -0.04
    ents
    -0.03
    ent
    -0.03
    N
    -0.03
    ange
    -0.03
    inal
    -0.03
    ency
    -0.03
    rite
    -0.03
    rom
    -0.02
    Positive Logits
    b
    0.05
    ¸
    0.04
    tive
    0.04
    g
    0.04
     sum
    0.03
    _sum
    0.03
    ts
    0.03
    et
    0.03
    tes
    0.03
    gment
    0.02
    Activations Density 79.027%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis before def

    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
    qrt
    -0.07
     return
    -0.07
    <|
    -0.06
    ating
    -0.05
    apping
    -0.05
     [[
    -0.04
    0
    -0.04
     tuple
    -0.04
     nx
    -0.04
     ("
    -0.03
    Positive Logits
    (file
    0.04
    jk
    0.04
    udoku
    0.03
    **
    0.03
     **
    0.03
    :↵
    0.03
     file
    0.03
    X
    0.03
    N
    0.03
     Ex
    0.03
    Activations Density 45.564%

    No Known Activations