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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ли
    1.15
    ר
    1.10
    นี
    0.99
    นั้น
    0.98
    ת
    0.98
     возможности
    0.97
    dır
    0.91
    ᅱ
    0.91
    ง่าย
    0.91
    ˋ
    0.90
    POSITIVE LOGITS
    तरंज
    1.03
    oghi
    1.00
    WORTH
    0.98
    ită
    0.98
    yd
    0.96
    uş
    0.95
    žno
    0.95
    HAL
    0.95
    iz
    0.93
     goles
    0.93
    Act Density 0.008%

    No Known Activations