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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lovely
    0.78
    न
    0.69
     technisch
    0.68
     wonderful
    0.67
    但是我
    0.67
     amazing
    0.66
    એ
    0.66
     estern
    0.66
     Mudah
    0.66
    ب
    0.65
    POSITIVE LOGITS
    要注意
    0.61
    坌
    0.54
    деся
    0.53
    ூர்
    0.53
    协会
    0.53
    要望
    0.52
    日期
    0.51
    תוך
    0.50
    邹
    0.50
     kiểm
    0.49
    Act Density 0.051%

    No Known Activations