INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     torque
    0.84
    mathemat
    0.81
    Transport
    0.79
     energy
    0.77
     thermodynamic
    0.76
    電流
    0.76
    ार्म
    0.75
     Physics
    0.75
     fairness
    0.74
     Gauss
    0.74
    POSITIVE LOGITS
     spoken
    1.07
     língua
    1.06
     langue
    1.06
     linguistic
    1.03
     lingua
    1.02
     LANGUAGE
    1.00
    0.99
     Linguistic
    0.98
     langage
    0.93
     زبان
    0.93
    Act Density 1.616%

    No Known Activations