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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     successivamente
    1.06
    gerät
    1.02
    ματα
    0.98
    tumor
    0.96
    يين
    0.94
     vervolgens
    0.93
     其实
    0.92
    thebetterindia
    0.92
     وعلى
    0.91
     Afterward
    0.91
    POSITIVE LOGITS
    곳
    1.13
    الأ
    1.04
    j
    1.02
    לה
    1.01
    ž
    0.98
    рей
    0.98
    א
    0.97
    ০১
    0.95
    ING
    0.95
    인
    0.93
    Act Density 0.124%

    No Known Activations