© 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

    try block start

    python-code · gemini-2.5-flash-lite

    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
    }:
    -0.10
    }
    -0.07
    ]][
    -0.07
    },
    -0.06
    ][
    -0.05
    }"
    -0.04
     [[
    -0.04
     assign
    -0.03
     function
    -0.03
    .append
    -0.03
    Positive Logits
    date
    0.05
     by
    0.04
    _by
    0.04
     temp
    0.03
    ink
    0.03
    `
    0.02
     based
    0.02
    ï
    0.02
    h
    0.02
    ...
    0.02
    Activations Density 99.995%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    is None or is not None

    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
    urrent
    -0.05
    uristic
    -0.04
    60
    -0.04
    [current
    -0.04
    (current
    -0.04
    .add
    -0.03
    join
    -0.03
     current
    -0.03
    current
    -0.03
    ė
    -0.03
    Positive Logits
    rior
    0.04
    lose
    0.03
     set
    0.03
    uration
    0.03
    place
    0.03
    ies
    0.03
    cess
    0.03
    ain
    0.02
    alue
    0.02
     continue
    0.02
    Activations Density 12.963%

    No Known Activations