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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     phía
    -0.07
     Zuk
    -0.07
    误
    -0.07
    老师的
    -0.07
     않는
    -0.07
    赦
    -0.07
    かもしれませんが
    -0.07
    imators
    -0.06
    rik
    -0.06
     isFirst
    -0.06
    POSITIVE LOGITS
     elimination
    0.08
     subtotal
    0.07
    сос
    0.07
    _social
    0.07
     buying
    0.07
    AJOR
    0.07
     Sass
    0.07
    --------------
    0.07
    	global
    0.07
     luggage
    0.07
    Act Density 0.047%

    No Known Activations