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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     be
    1.55
     zacz
    1.40
     apare
    1.35
    ้
    1.31
     indique
    1.20
     lanz
    1.19
     ocult
    1.19
     observado
    1.19
    for
    1.17
     ufficial
    1.17
    POSITIVE LOGITS
    ات
    1.08
    с
    1.08
    сны
    1.07
    る
    1.07
    től
    1.05
    сна
    1.02
    라인
    1.02
    hydrox
    1.00
    در
    0.99
    ో
    0.99
    Act Density 0.000%

    No Known Activations