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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     inim
    0.48
     Сара
    0.44
    लंघन
    0.44
     Ahab
    0.43
     Salz
    0.41
     Feuer
    0.41
     निजामा
    0.41
    فون
    0.41
     میتوان
    0.40
     Oğ
    0.40
    POSITIVE LOGITS
    o
    0.52
     απαι
    0.47
    t
    0.46
    រយៈពេល
    0.42
    label
    0.41
    max
    0.41
    តិ
    0.40
     upgrading
    0.40
    矮
    0.40
    gn
    0.40
    Act Density 0.002%

    No Known Activations