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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    raiser
    0.77
    variety
    0.73
     ассорти
    0.70
    newsletter
    0.69
    тельный
    0.69
    言い
    0.69
     プラス
    0.69
    رحله
    0.69
    ບໍ
    0.68
     финансо
    0.68
    POSITIVE LOGITS
    0.77
    {
    0.73
     silice
    0.66
    í
    0.66
    .:
    0.65
     includ
    0.64
    ]).
    0.64
     during
    0.64
     undoubtedly
    0.64
     FabD
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.