© 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. 1254
    Prev
    Next
    INDEX
    Explanations

    argument access within list comprehensions (negative activations)

    python-code · gemini-2.5-flash-lite

    dictionary assignments and return values

    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
    _idx
    -0.13
     zip
    -0.09
    (map
    -0.06
    _str
    -0.06
     List
    -0.05
     In
    -0.03
     up
    -0.03
     ele
    -0.03
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
     dictionary
    0.36
    dict
    0.33
    .values
    0.27
     dict
    0.27
    ctionary
    0.26
    _dict
    0.24
    .keys
    0.23
    .items
    0.22
    keys
    0.19
    apping
    0.17
    Activations Density 100.000%

    No Known Activations