© 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

    index of list or array (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
     nx
    -0.13
     elif
    -0.11
     ny
    -0.11
    ize
    -0.09
    yp
    -0.09
    lf
    -0.07
    ave
    -0.07
    ust
    -0.07
    one
    -0.07
    raw
    -0.06
    Positive Logits
    [start
    0.25
    (start
    0.21
    _start
    0.20
    ighbor
    0.18
    (neighbor
    0.17
    _end
    0.16
     neighbors
    0.16
    start
    0.16
     end
    0.15
     start
    0.15
    Activations Density 91.117%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    lambda function argument

    python-code · gemini-2.5-flash-lite

    indexing a list with 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
     P
    -0.05
    graph
    -0.04
    P
    -0.04
    oin
    -0.03
    p
    -0.03
    rt
    -0.02
    ast
    -0.02
    essage
    -0.01
    ile
    -0.01
    list
    -0.01
    Positive Logits
    utation
    0.05
    gth
    0.05
    ain
    0.04
    ake
    0.04
    _dict
    0.03
    an
    0.03
    inal
    0.03
    apping
    0.03
    isit
    0.03
    in
    0.03
    Activations Density 100.000%

    No Known Activations