© 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
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. Residual Stream
    5. 7-RESID
    6. 1552
    Prev
    Next
    INDEX
    Explanations

    list comprehension `[_ for _ in range(...)]` (negative activations)

    python-code · gemini-2.5-flash-lite

    keyword arguments in function definitions

    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
     Def
    -0.19
     Initial
    -0.16
    ing
    -0.12
     float
    -0.12
    alc
    -0.12
     Testing
    -0.09
     False
    -0.05
     Find
    -0.04
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
    arg
    0.17
     Initialize
    0.13
     Define
    0.12
    .randint
    0.11
     Create
    0.11
     Calculate
    0.09
     the
    0.02
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 98.983%

    No Known Activations