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

    Neuronpedia

    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GPS
    -0.08
    出动
    -0.06
    赪
    -0.06
    黑洞
    -0.06
    orsi
    -0.06
     Москве
    -0.06
    样子
    -0.06
    CGSize
    -0.06
     tightly
    -0.06
     bows
    -0.06
    POSITIVE LOGITS
     recib
    0.07
    商業
    0.07
    responsive
    0.07
     helpers
    0.07
     scop
    0.07
    떡
    0.06
     Everyday
    0.06
    睡眠
    0.06
    prop
    0.06
    เร
    0.06
    Act Density 0.021%

    No Known Activations