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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     сказать
    0.88
     decir
    0.84
     слегка
    0.83
     ‘‘
    0.82
     বিরুদ্ধে
    0.82
     hukuk
    0.82
     olhar
    0.81
    璺
    0.81
    inuous
    0.80
    litt
    0.79
    POSITIVE LOGITS
    Від
    0.88
    Tre
    0.79
    ships
    0.76
    秏
    0.75
    Ж
    0.74
    中医
    0.73
     Phase
    0.73
     Div
    0.71
    الصف
    0.69
    Т
    0.69
    Act Density 0.000%

    No Known Activations