© 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

    command argument

    python-code · gemini-2.5-flash-lite

    function arguments or list elements (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
    .graph
    -0.09
    No
    -0.08
     lab
    -0.08
    .node
    -0.08
     coordinates
    -0.08
    J
    -0.08
     lat
    -0.08
     bre
    -0.07
     loc
    -0.07
    Z
    -0.07
    Positive Logits
    _c
    0.07
    _m
    0.05
     _
    0.04
    Ĺ
    0.04
     or
    0.04
     pro
    0.04
    _
    0.04
    ._
    0.04
    (pro
    0.03
    .m
    0.03
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    heapq operations or list pop

    python-code · gemini-2.5-flash-lite

    `d` followed by `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
    rent
    -0.10
    rap
    -0.09
    ump
    -0.08
    ffic
    -0.07
    hest
    -0.07
    rom
    -0.06
    ory
    -0.06
    ong
    -0.06
    are
    -0.06
    ile
    -0.06
    Positive Logits
    roup
    0.06
    xF
    0.05
    ´
    0.05
    x
    0.04
     Check
    0.04
    ude
    0.04
    heck
    0.04
    _move
    0.04
    cies
    0.04
    í
    0.04
    Activations Density 100.000%

    No Known Activations