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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ختی
    0.80
     vigorous
    0.77
     leafy
    0.75
     doesn
    0.74
    adisu
    0.73
     blushing
    0.73
     purging
    0.73
     lips
    0.72
    ێر
    0.72
    斯的
    0.71
    POSITIVE LOGITS
    됨
    0.86
    นม
    0.78
    BODY
    0.75
    stanford
    0.71
    BL
    0.69
     новый
    0.69
     नौ
    0.69
     первой
    0.69
     единственный
    0.69
     семь
    0.68
    Act Density 0.001%

    No Known Activations