© 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

    parentheses or multiplication operator

    python-code · gemini-2.5-flash-lite

    list index access (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
    (new
    -0.05
    reate
    -0.03
     as
    -0.03
     **
    -0.03
     new
    -0.03
    as
    -0.03
     second
    -0.03
     at
    -0.03
    ]['
    -0.03
    ine
    -0.03
    Positive Logits
    ran
    0.07
     ran
    0.06
    ise
    0.05
    udok
    0.05
    .ran
    0.04
    dom
    0.04
    rior
    0.04
    join
    0.04
    rue
    0.04
    rect
    0.04
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations
    No Explanations Found
    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
     d
    -0.16
     return
    -0.07
     are
    -0.06
     al
    -0.04
    lf
    -0.02
    ut
    -0.01
     not
    -0.01
    ch
    -0.01
    >
    -0.00
    .start
    -0.00
    Positive Logits
    ion
    0.09
    ues
    0.08
    ess
    0.07
    ork
    0.07
    atri
    0.07
    urn
    0.07
    rack
    0.07
    ud
    0.06
    ook
    0.06
    rom
    0.06
    Activations Density 20.911%

    No Known Activations