© 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

    .append method call (negative activations)

    python-code · gemini-2.5-flash-lite

    index access with `]`

    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
    .keys
    -0.07
    .append
    -0.06
    ()↵
    -0.04
    ][
    -0.03
     -=
    -0.02
    .remove
    -0.02
     +=
    -0.02
     If
    -0.02
    .write
    -0.02
    .add
    -0.02
    Positive Logits
     found
    0.03
    ["
    0.02
     ("
    0.02
    ['
    0.02
     (
    0.02
     (-
    0.02
    uel
    0.02
     ('
    0.02
     ((
    0.02
    over
    0.02
    Activations Density 99.769%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method call parentheses (negative activations)

    python-code · gemini-2.5-flash-lite

    .child or .header

    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
    }:
    -0.11
    }
    -0.08
    }"
    -0.06
    },
    -0.06
    '.
    -0.03
     found
    -0.02
    ]
    -0.01
    op
    -0.01
    ax
    -0.01
    id
    -0.01
    Positive Logits
    rior
    0.02
    lose
    0.02
    uration
    0.01
    ies
    0.01
    .co
    0.01
    alue
    0.01
     out
    0.01
    ness
    0.01
    endencies
    0.01
    du
    0.01
    Activations Density 58.746%

    No Known Activations