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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    η
    1.46
    nbsp
    1.39
    ה
    1.39
    1.35
    stit
    1.34
    ва
    1.30
    vä
    1.23
    नांतर
    1.23
     долла
    1.22
     albeit
    1.20
    POSITIVE LOGITS
    样子
    1.08
    艶
    1.03
    其
    1.02
     مع
    1.01
     locomotion
    0.98
    ญา
    0.96
    ანა
    0.95
     부
    0.95
    ات
    0.95
    ীক
    0.94
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.