Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    args

    np_max-act · gemini-2.0-flash

    Python code snippets defining decorators that create FastAPI endpoints.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron specifically detects use of Python’s varargs/keyword‐args syntax (the “*args” and “**kwargs” patterns) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    IMATION
    -0.07
     Converter
    -0.07
    出了
    -0.06
    516
    -0.06
     Humans
    -0.06
    _hit
    -0.06
    like
    -0.06
    _RETRY
    -0.06
    Accordion
    -0.06
    -solving
    -0.06
    POSITIVE LOGITS
    (ListNode
    0.07
    ницип
    0.07
     д
    0.07
     quantitative
    0.07
     Whole
    0.06
     différent
    0.06
    zej
    0.06
    aviest
    0.06
    args
    0.06
     ntohs
    0.06
    Act Density 0.001%

    No Known Activations