© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 724
    Prev
    Next
    INDEX
    Explanations

    list comprehension 'for' keyword (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute access or method calls

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ordinates
    -0.21
    stination
    -0.20
     represent
    -0.20
    à
    -0.17
    _coordinates
    -0.17
    osition
    -0.17
    strip
    -0.16
    _position
    -0.16
     adjac
    -0.16
    ination
    -0.15
    POSITIVE LOGITS
    _len
    0.17
    _pos
    0.14
    use
    0.14
    _idx
    0.14
    val
    0.13
     dist
    0.13
    dist
    0.12
     val
    0.12
    _str
    0.12
    ow
    0.12
    Activations Density 100.000%

    No Known Activations