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

    Neuronpedia

    INDEX
    Explanations

    information and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    那些
    0.60
     deveria
    0.57
     وطالبات
    0.57
    最具
    0.56
    리의
    0.55
    сант
    0.55
     должны
    0.54
     최대한
    0.54
     reembolso
    0.54
    ását
    0.53
    POSITIVE LOGITS
     available
    1.30
     vorhanden
    1.21
     disponible
    1.02
     involved
    1.02
     going
    1.01
     disponível
    1.00
     disponibles
    0.96
     underway
    0.92
    available
    0.91
     goin
    0.91
    Act Density 0.245%

    No Known Activations