© 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

    not followed by comparison or boolean

    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
    nt
    -0.05
    c
    -0.04
     Calculate
    -0.04
    ain
    -0.03
    vai
    -0.03
    etween
    -0.03
    ties
    -0.03
    co
    -0.03
    erate
    -0.03
    ty
    -0.03
    Positive Logits
    uristic
    0.07
    60
    0.06
    ile
    0.05
    46
    0.04
    I
    0.03
    v
    0.03
    55
    0.02
    red
    0.02
    ust
    0.02
    set
    0.02
    Activations Density 46.195%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment or comparison (negative activations)

    python-code · gemini-2.5-flash-lite

    dictionary keys and assignments

    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
    +
    -0.05
     +
    -0.05
    div
    -0.04
    args
    -0.04
    append
    -0.04
     +=
    -0.03
    .append
    -0.02
    ?
    -0.02
    ep
    -0.02
    }:
    -0.02
    Positive Logits
    =True
    0.02
    .pop
    0.02
    tity
    0.02
    tail
    0.01
    _for
    0.01
     return
    0.01
    ["
    0.01
    cep
    0.00
    rice
    0.00
     ro
    0.00
    Activations Density 86.710%

    No Known Activations