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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    解決
    -0.07
    нибуд
    -0.07
    .price
    -0.07
    下面小编
    -0.06
     Advantage
    -0.06
     становится
    -0.06
    .Std
    -0.06
    /options
    -0.06
    竫
    -0.06
    (Grid
    -0.06
    POSITIVE LOGITS
    羲
    0.07
     כ
    0.07
     itemCount
    0.07
    招收
    0.07
    学前
    0.06
     طفل
    0.06
     энер
    0.06
    Mission
    0.06
     школ
    0.06
    .imp
    0.06
    Act Density 0.001%

    No Known Activations