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

    Neuronpedia

    INDEX
    Explanations

    numbers and amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Remote
    0.59
     Navigation
    0.58
     Ideal
    0.57
     bắt
    0.55
     东
    0.54
     Security
    0.54
     Learning
    0.54
     Tạo
    0.54
     为了
    0.53
     Mechanical
    0.53
    POSITIVE LOGITS
     cifra
    0.86
    數字
    0.81
     numbers
    0.80
     cifras
    0.78
    numbers
    0.78
    金額
    0.77
     chiffres
    0.76
     циф
    0.75
    数値
    0.70
     ಸಂಖ್ಯ
    0.70
    Act Density 0.231%

    No Known Activations