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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ак
    0.91
     і
    0.86
     ам
    0.75
     tannin
    0.73
    revolutionary
    0.73
    ва
    0.72
     ін
    0.71
     ago
    0.70
     şi
    0.70
     підтрим
    0.70
    POSITIVE LOGITS
    ené
    0.84
     möjligt
    0.84
    ленный
    0.81
    тном
    0.81
    тился
    0.80
    ленное
    0.79
    끔
    0.78
    ený
    0.77
    eis
    0.77
    ленным
    0.77
    Act Density 0.002%

    No Known Activations