© 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

    identifier followed by assignment (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
    instance
    -0.06
    join
    -0.06
    riority
    -0.05
    cores
    -0.05
     sorted
    -0.05
    [str
    -0.05
    keys
    -0.04
    [int
    -0.04
    output
    -0.04
    hip
    -0.04
    Positive Logits
    ili
    0.18
    gle
    0.17
    ility
    0.16
    zz
    0.15
    ount
    0.14
    vious
    0.14
    ket
    0.14
    ilities
    0.14
    ble
    0.13
    gor
    0.13
    Activations Density 6.442%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    slice notation with step

    python-code · gemini-2.5-flash-lite

    expression in list comprehension (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
    uzzle
    -0.16
    udoku
    -0.14
    gram
    -0.12
    oard
    -0.11
    inal
    -0.11
    .graph
    -0.10
    (graph
    -0.09
    _graph
    -0.09
     graph
    -0.09
    udok
    -0.09
    Positive Logits
    #
    0.11
     #
    0.10
    um
    0.07
    ity
    0.06
    rt
    0.06
    ities
    0.06
     move
    0.06
    gion
    0.05
    hest
    0.05
    erson
    0.05
    Activations Density 100.000%

    No Known Activations