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

    Neuronpedia

    INDEX
    Explanations

    chào trân trọng

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Restaurants
    0.80
    કિંગ
    0.80
    カー
    0.77
    Pittsburgh
    0.75
    Risk
    0.74
    Choisissez
    0.73
    Suppose
    0.72
    Ticket
    0.71
    Tourism
    0.71
     Букмекерлар
    0.71
    POSITIVE LOGITS
     chưa
    0.72
     có
    0.71
     chủ
    0.69
     nothing
    0.66
     tất
    0.64
     nhanh
    0.63
     khi
    0.62
     điện
    0.62
     thứ
    0.61
     nguyên
    0.61
    Act Density 0.001%

    No Known Activations