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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    いている
    0.39
    ड़क
    0.38
    alic
    0.37
    కొని
    0.36
    āk
    0.35
    ناسب
    0.35
     jantar
    0.35
    驰
    0.35
     tallest
    0.35
    образие
    0.35
    POSITIVE LOGITS
     όταν
    0.40
     כאשר
    0.39
     cuando
    0.39
    тэ
    0.39
     lorsqu
    0.38
    หลัง
    0.36
    when
    0.36
     जेव्हा
    0.36
     khi
    0.34
     וכ
    0.34
    Act Density 0.000%

    No Known Activations