© 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. 1730
    Prev
    Next
    INDEX
    Explanations

    random.choice and json.loads (negative activations)

    python-code · gemini-2.5-flash-lite

    `else` or `in` keywords

    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
    o
    -0.22
    own
    -0.20
     o
    -0.20
    oc
    -0.19
    od
    -0.17
    ok
    -0.16
    ore
    -0.16
    ow
    -0.12
    ho
    -0.12
    over
    -0.11
    POSITIVE LOGITS
     order
    0.06
    &
    0.00
    #
    0.00
    '
    0.00
    *
    0.00
    %
    0.00
    )
    0.00
    !
    0.00
    "
    0.00
    $
    0.00
    Activations Density 100.000%

    No Known Activations