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

    Neuronpedia

    INDEX
    Explanations

    measure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dó
    -0.07
     отзывы
    -0.07
     IOS
    -0.07
     Bett
    -0.07
    结算
    -0.07
    (xx
    -0.07
     getId
    -0.07
     Tod
    -0.07
     иг
    -0.07
    Empty
    -0.07
    POSITIVE LOGITS
    :<?
    0.08
    	float
    0.07
    一般是
    0.07
    宬
    0.07
    رون
    0.07
     Albums
    0.07
    措施
    0.07
     За
    0.07
    سهل
    0.07
    covers
    0.07
    Act Density 0.041%

    No Known Activations