© 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

    0

    python-code · gemini-2.5-flash-lite

    the number zero (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
    ]]↵
    -0.10
    )]↵
    -0.08
    ].
    -0.07
    '↵
    -0.07
     __
    -0.07
    "↵
    -0.07
    )↵
    -0.06
    )):↵
    -0.06
    }↵
    -0.06
     []↵
    -0.06
    Positive Logits
    umn
    0.16
    gs
    0.08
    stance
    0.07
    utput
    0.06
    g
    0.05
     index
    0.05
     Testing
    0.04
    resh
    0.04
    }"
    0.04
     np
    0.03
    Activations Density 4.749%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment using '=' (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
    .txt
    -0.09
    xp
    -0.06
    tex
    -0.06
    mport
    -0.06
    ft
    -0.06
    fset
    -0.06
    64
    -0.05
    ink
    -0.05
    rc
    -0.04
    mbol
    -0.04
    Positive Logits
    .is
    0.11
    work
    0.10
    .num
    0.09
    .in
    0.08
     file
    0.07
    ..
    0.06
    ork
    0.05
     var
    0.04
    .re
    0.03
    straint
    0.03
    Activations Density 3.185%

    No Known Activations