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

    Neuronpedia

    INDEX
    Explanations

    right triangle hypotenuse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whispers
    -0.08
     понять
    -0.07
    /i
    -0.07
     sile
    -0.07
     exams
    -0.07
     интел
    -0.07
    unnable
    -0.07
    sil
    -0.07
     tonnes
    -0.07
     silic
    -0.07
    POSITIVE LOGITS
    跑路
    0.09
    ानो
    0.08
     拉菲
    0.08
     पहु
    0.08
    зода
    0.08
    पी
    0.08
    相关阅读
    0.08
    备用网址
    0.08
     coneg
    0.08
     Perho
    0.08
    Act Density 0.027%

    No Known Activations