© 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. 816
    Prev
    Next
    INDEX
    Explanations

    key = lambda (negative activations)

    python-code · gemini-2.5-flash-lite

    random.randrange or random.randint function calls

    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
    lat
    -0.26
    at
    -0.26
     at
    -0.25
    ator
    -0.18
    ve
    -0.10
    name
    -0.09
    45
    -0.08
    -0.05
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
    er
    0.18
    ra
    0.15
    u
    0.14
    V
    0.06
    ]
    0.05
     i
    0.03
    "
    0.03
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 98.959%

    No Known Activations