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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ような
    0.91
    ように
    0.88
     вроде
    0.77
     لذا
    0.70
     حاضر
    0.68
     kuten
    0.68
     கொண்டே
    0.68
    ため
    0.67
     জন্য
    0.67
    ために
    0.67
    POSITIVE LOGITS
    rı
    0.77
     mógł
    0.77
    з
    0.77
    tı
    0.75
    ból
    0.75
    ップ
    0.75
     differs
    0.74
    té
    0.74
    পল
    0.73
     disapproved
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.