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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    அ
    0.87
     Тому
    0.86
    <0xBA>
    0.81
    ין
    0.75
    ק
    0.75
     А
    0.75
    心脏
    0.75
    اع
    0.74
    Besides
    0.74
    ન
    0.73
    POSITIVE LOGITS
     términos
    0.85
    shu
    0.83
    ни
    0.81
    sh
    0.80
    ේද
    0.80
    stm
    0.78
    тура
    0.77
     Möbel
    0.77
     emple
    0.75
    ッション
    0.75
    Act Density 0.000%

    No Known Activations