© 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
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. Residual Stream
    5. 7-RESID
    6. 1874
    Prev
    Next
    INDEX
    Explanations

    `__name__ ==` (negative activations)

    python-code · gemini-2.5-flash-lite

    for loop iteration

    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
    py
    -0.29
    dule
    -0.25
    uil
    -0.21
     sys
    -0.15
     code
    -0.15
     run
    -0.14
    gorithm
    -0.13
    ases
    -0.13
     sc
    -0.12
     main
    -0.12
    POSITIVE LOGITS
    adjac
    0.17
    uccess
    0.15
     conne
    0.13
    duct
    0.12
    ag
    0.10
    il
    0.09
    ong
    0.09
    con
    0.07
    is
    0.04
    '
    0.00
    Activations Density 100.000%

    No Known Activations