© 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

    variable name followed by 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
     start
    -0.01
    &
    0.00
    #
    0.00
    '
    0.00
    *
    0.00
    %
    0.00
    )
    0.00
    !
    0.00
    "
    0.00
    $
    0.00
    Positive Logits
     parse
    0.05
     __
    0.04
     solve
    0.04
     Graph
    0.04
     q
    0.04
     break
    0.04
     dp
    0.04
     del
    0.03
     bre
    0.03
     default
    0.03
    Activations Density 3.721%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method name 'i'

    python-code · gemini-2.5-flash-lite

    `create_` methods or `__` methods (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
    etween
    -0.09
     Calculate
    -0.08
     Graph
    -0.07
     enumerate
    -0.06
    timal
    -0.06
     abs
    -0.06
     math
    -0.05
    raph
    -0.05
     Re
    -0.05
    udoku
    -0.05
    Positive Logits
     ]↵
    0.08
     }↵
    0.07
     },↵
    0.07
    0.06
    pe
    0.05
    et
    0.05
    .add
    0.04
    0.04
    ='
    0.04
     dictionary
    0.03
    Activations Density 100.000%

    No Known Activations