INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    对象
    0.63
    对象的
    0.50
    オブジェクト
    0.47
    OBJECT
    0.46
     Objekt
    0.45
     对象
    0.45
     objekt
    0.42
     OBJECT
    0.42
     Obj
    0.41
    0.41
    POSITIVE LOGITS
     goal
    2.48
    Goal
    2.36
     Goal
    2.36
    goal
    2.34
     goals
    2.03
     Goals
    2.02
    Goals
    1.96
    goals
    1.92
     गोल
    1.70
     gol
    1.66
    Act Density 0.028%

    No Known Activations