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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ları
    1.00
    둰
    0.91
     Hota
    0.85
    ঃখ
    0.84
    lar
    0.82
    อื่น
    0.81
     וכ
    0.79
    циях
    0.79
    ्रिय
    0.78
    ନ୍ତ
    0.78
    POSITIVE LOGITS
     والذي
    0.86
    hooting
    0.81
     onde
    0.80
     inteligente
    0.75
     जीतने
    0.71
     chuột
    0.68
    cante
    0.68
     ktorý
    0.68
     Brace
    0.67
    getAction
    0.67
    Act Density 0.001%

    No Known Activations