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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     đây
    0.51
    知道
    0.51
     gennaio
    0.51
    TH
    0.50
     то
    0.49
    يد
    0.47
    Altri
    0.47
    ם
    0.47
     في
    0.46
     toàn
    0.46
    POSITIVE LOGITS
    arier
    0.49
    zan
    0.46
    shuffle
    0.46
    0.45
     Vertrieb
    0.45
     aversion
    0.45
     ஆண்டுகளுக்கு
    0.44
    amsmath
    0.44
    sef
    0.43
     врача
    0.43
    Act Density 0.000%

    No Known Activations