© 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

    string membership check (negative activations)

    python-code · gemini-2.5-flash-lite

    `★` character in code snippets

    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
    o
    -0.04
                       
    -0.03
    O
    -0.03
                           
    -0.03
                   
    -0.03
                    
    -0.02
                    ↵
    -0.02
    ield
    -0.02
    one
    -0.02
                  
    -0.02
    Positive Logits
    ↵            ↵
    0.01
    ↵    ↵
    0.01
    ↵        ↵
    0.01
     c
    0.01
             
    0.01
    =
    0.00
    quired
    0.00
     -=
    0.00
    '
    0.00
    #
    0.00
    Activations Density 86.889%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    return statement argument (negative activations)

    python-code · gemini-2.5-flash-lite

    call arguments

    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
     Testing
    -0.04
     Test
    -0.04
    print
    -0.03
     Output
    -0.03
    pected
    -0.03
     output
    -0.02
    udoku
    -0.02
    !
    -0.02
    sert
    -0.02
    (point
    -0.02
    Positive Logits
     {↵
    0.03
     {'
    0.03
     {"
    0.03
    e
    0.03
    ark
    0.02
    ce
    0.02
    ":
    0.02
     e
    0.02
    ist
    0.02
     len
    0.02
    Activations Density 98.358%

    No Known Activations