© 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

    Python string literal

    python-code · gemini-2.5-flash-lite

    string method .lower() (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
     pass
    -0.04
    w
    -0.04
    ass
    -0.04
     instruction
    -0.04
    W
    -0.04
    _w
    -0.04
     W
    -0.04
    .w
    -0.03
     instructions
    -0.03
     weights
    -0.03
    Positive Logits
    ili
    0.07
    gle
    0.06
    ility
    0.06
    ket
    0.06
    ilities
    0.06
    tions
    0.06
    gor
    0.06
     person
    0.05
    ount
    0.05
    ties
    0.05
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    first element in a list or tuple definition (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
    ateg
    -0.11
    cel
    -0.10
    uccess
    -0.08
    X
    -0.08
    xF
    -0.07
    arent
    -0.07
    xb
    -0.07
    otal
    -0.07
    xc
    -0.06
    xf
    -0.06
    Positive Logits
    ce
    0.08
    ec
    0.07
    da
    0.05
    fe
    0.05
    ry
    0.05
    (N
    0.04
     ran
    0.04
    ef
    0.04
     t
    0.04
     dp
    0.03
    Activations Density 50.473%

    No Known Activations