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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝘏
    0.80
    ਜੀ
    0.77
     উদ্দেশে
    0.74
    う
    0.73
    𝗼
    0.72
    ों
    0.72
    ിയ
    0.71
    ताब
    0.71
    簱
    0.71
    ిత
    0.71
    POSITIVE LOGITS
     el
    0.80
     \&
    0.74
     prendere
    0.74
    yers
    0.72
     piu
    0.71
     wohl
    0.68
     کئے
    0.68
     âg
    0.67
     Тран
    0.67
     dari
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.