© 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

    argument name in function call (negative activations)

    python-code · gemini-2.5-flash-lite

    numeric literal following dot

    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
    !
    -0.06
    ..
    -0.04
    ?
    -0.04
    ...
    -0.04
    ^
    -0.02
    <
    -0.02
    >
    -0.02
     given
    -0.02
    -0.02
    sert
    -0.01
    Positive Logits
    000
    0.04
     heap
    0.01
     function
    0.01
     True
    0.01
     contain
    0.01
     check
    0.01
    }
    0.00
    )
    0.00
    ing
    0.00
    '
    0.00
    Activations Density 65.300%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    date of birth (negative activations)

    python-code · gemini-2.5-flash-lite

    loop iteration or indexing

    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
     break
    -0.02
     set
    -0.02
    _si
    -0.02
    0
    -0.01
    ap
    -0.01
    il
    -0.01
    ",↵
    -0.01
    O
    -0.01
     "
    -0.00
     else
    -0.00
    Positive Logits
    _end
    0.03
    oal
    0.03
    end
    0.03
     end
    0.03
     goal
    0.03
    arget
    0.03
     destination
    0.02
     target
    0.02
    instance
    0.02
    right
    0.02
    Activations Density 20.475%

    No Known Activations