© 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

    `del` keyword or beginning of `denominator`

    python-code · gemini-2.5-flash-lite

    attribute access or dictionary key (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
    þ
    -0.09
    ü
    -0.09
    ö
    -0.09
    À
    -0.09
    <invalid_2046>
    -0.09
    ÷
    -0.09
    ù
    -0.09
    ý
    -0.09
    õ
    -0.09
    ÿ
    -0.09
    Positive Logits
     representing
    0.09
     that
    0.06
     given
    0.05
     each
    0.05
     the
    0.05
     represe
    0.05
     based
    0.04
     and
    0.04
     whe
    0.04
     usage
    0.03
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    instance attribute 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
    ility
    -0.08
    ilities
    -0.08
    ket
    -0.08
     whe
    -0.08
    .position
    -0.07
     closest
    -0.07
    us
    -0.07
    ili
    -0.06
    gle
    -0.06
     '
    -0.06
    Positive Logits
    xF
    0.16
    join
    0.12
    rib
    0.11
    umn
    0.11
    ber
    0.11
    ion
    0.11
    µ
    0.09
    ate
    0.09
    atri
    0.09
    ency
    0.09
    Activations Density 99.510%

    No Known Activations