© 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

    collections module imports (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
    ry
    -0.09
                    ↵
    -0.06
    [j
    -0.06
    Į
    -0.05
    ram
    -0.05
    qrt
    -0.04
     []↵↵
    -0.04
    ")↵↵
    -0.04
     {}↵↵
    -0.04
    rc
    -0.04
    Positive Logits
    ):↵
    0.07
    utation
    0.07
    )
    0.07
    gth
    0.06
    }:
    0.06
    (N
    0.05
    ']
    0.05
     ex
    0.05
    (self
    0.05
    ])
    0.05
    Activations Density 85.697%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    index and value iteration with enumerate

    python-code · gemini-2.5-flash-lite

    indexing a list or tuple (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
    uzzle
    -0.07
    /
    -0.07
    udok
    -0.06
    gest
    -0.06
    mpty
    -0.06
    uzz
    -0.06
    ('
    -0.06
    ^
    -0.05
    ake
    -0.05
    udoku
    -0.05
    Positive Logits
     colle
    0.07
    rue
    0.06
    },↵
    0.05
    ateg
    0.05
    ).
    0.05
     operation
    0.05
    ]):↵
    0.05
     oper
    0.05
    ome
    0.04
    ):
    0.04
    Activations Density 100.000%

    No Known Activations