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

    Neuronpedia

    INDEX
    Explanations

    precise calculation and approximation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    だから
    0.47
     suficientes
    0.47
     Nationwide
    0.43
     Nazionale
    0.43
     suficiente
    0.43
     Funds
    0.42
     नेशनल
    0.42
    スペース
    0.41
     ആരോപ
    0.41
    роде
    0.41
    POSITIVE LOGITS
     calculations
    0.59
     calculation
    0.59
    Calculating
    0.57
     cálculo
    0.57
    Calculation
    0.55
    計算
    0.53
    计算
    0.51
     계산
    0.50
     Berechnung
    0.49
    calculate
    0.49
    Act Density 0.001%

    No Known Activations