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

    Neuronpedia

    INDEX
    Explanations

    The number 8

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially legal citation numbers and section references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    刷
    -0.08
     prostředí
    -0.07
    ipar
    -0.07
    	dataType
    -0.06
     یافت
    -0.06
    ове
    -0.06
    ný
    -0.06
    оля
    -0.06
    (infile
    -0.06
    _water
    -0.06
    POSITIVE LOGITS
     Advice
    0.07
     Expense
    0.06
     Resets
    0.06
    =create
    0.06
    有限
    0.06
     Affiliate
    0.06
     قرن
    0.06
    ώρα
    0.06
     Clash
    0.06
     Ki
    0.06
    Act Density 0.002%

    No Known Activations