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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     weakens
    0.44
     वायरल
    0.43
     Телефон
    0.41
     Networks
    0.41
     htob
    0.41
     ফোন
    0.41
     Dienstag
    0.40
    内部
    0.40
     idő
    0.40
     Infectious
    0.40
    POSITIVE LOGITS
    つ
    0.43
    뷊
    0.42
    ってる
    0.41
    اليه
    0.40
    오
    0.40
    ଚ
    0.40
    공
    0.38
    ཝ
    0.38
     Projet
    0.38
    0.38
    Act Density 0.000%

    No Known Activations