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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ل
    0.95
    র
    0.92
    ка
    0.91
    𝔯
    0.87
    ור
    0.87
    NAME
    0.79
    важа
    0.79
    नांक
    0.78
    কেন্ড
    0.78
    یه
    0.76
    POSITIVE LOGITS
     Careers
    0.89
     Volcano
    0.83
     debajo
    0.76
    Careers
    0.76
    Hearts
    0.76
     неболь
    0.75
     descub
    0.75
    衷
    0.74
    Ethics
    0.72
    Wings
    0.71
    Act Density 0.000%

    No Known Activations