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

    Neuronpedia

    INDEX
    Explanations

    Python *args **kwargs

    np_max-act · gemini-2.0-flash

    The neuron fires on Python’s variadic argument unpacking syntax (the `*args` and `**kwargs` parameters or call-site unpack operators).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iking
    -0.07
    thead
    -0.07
    ison
    -0.07
    Coverage
    -0.06
    反应
    -0.06
     Copper
    -0.06
    акон
    -0.06
    (actions
    -0.06
    ("-");↵
    -0.06
     Cass
    -0.06
    POSITIVE LOGITS
    routine
    0.07
     samo
    0.06
     Gaga
    0.06
     franç
    0.06
     Numerous
    0.06
    侯
    0.06
    _program
    0.06
     inspir
    0.06
     ROAD
    0.06
     طرح
    0.06
    Act Density 0.004%

    No Known Activations