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

    Neuronpedia

    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. 1648
    Prev
    Next
    INDEX
    Explanations

    variable unpacking in comprehensions (negative activations)

    python-code · gemini-2.5-flash-lite

    range( or is followed by None/not/in

    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
    get
    -0.08
    _f
    -0.03
    &
    0.00
    #
    0.00
    '
    0.00
    *
    0.00
    %
    0.00
    )
    0.00
    !
    0.00
    "
    0.00
    POSITIVE LOGITS
    ener
    0.20
     range
    0.19
     None
    0.16
     False
    0.15
     True
    0.14
    (st
    0.08
    In
    0.06
     l
    0.03
    '
    0.00
    #
    0.00
    Activations Density 99.268%

    No Known Activations