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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    стру
    0.45
    ことになる
    0.39
    ີ່ມ
    0.38
    틋
    0.37
     soddisf
    0.37
    漂亮的
    0.37
    幸せ
    0.36
    SystemCall
    0.36
     vendido
    0.36
    udni
    0.35
    POSITIVE LOGITS
     이에
    0.40
    دخل
    0.40
     եւ
    0.39
     ด่า
    0.39
     teasing
    0.38
    kern
    0.38
    िलायंस
    0.37
    sik
    0.37
     අවශ්‍ය
    0.37
     করিয়াছি
    0.36
    Act Density 0.002%

    No Known Activations