© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    collections.defaultdict or deque (negative activations)

    python-code · gemini-2.5-flash-lite

    `__name__` special variable

    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
    que
    -0.17
    ay
    -0.10
    als
    -0.08
    si
    -0.07
    args
    -0.06
    75
    -0.06
    dict
    -0.06
     by
    -0.04
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
    tices
    0.32
    tity
    0.28
    ti
    0.27
    tic
    0.21
    tive
    0.20
    tile
    0.20
    port
    0.12
    ost
    0.11
    ci
    0.08
    al
    0.03
    Activations Density 97.658%

    No Known Activations