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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    This neuron activates whenever it sees a numeric token (digits or decimals), i.e. it flags numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _texts
    -0.07
    ché
    -0.06
    —it
    -0.06
    	get
    -0.06
    ,args
    -0.06
     stol
    -0.06
     Parent
    -0.06
    _topics
    -0.06
     досяг
    -0.06
    scenes
    -0.06
    POSITIVE LOGITS
    shine
    0.06
    كتور
    0.06
     Kot
    0.06
     Đ
    0.06
     부산
    0.06
     devise
    0.06
     descriptive
    0.06
     Designed
    0.06
     pesticide
    0.06
    enties
    0.06
    Act Density 0.003%

    No Known Activations