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

    Neuronpedia

    INDEX
    Explanations

    durations of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Month
    0.51
     month
    0.50
     week
    0.50
    week
    0.47
     minuten
    0.46
     mensuales
    0.46
     млрд
    0.45
    Month
    0.45
     Week
    0.45
     tháng
    0.44
    POSITIVE LOGITS
    couple
    0.49
     couple
    0.47
    Couple
    0.43
     пару
    0.41
     birkaç
    0.41
    ܢܐ
    0.40
     ഒന്ന്
    0.39
     Couple
    0.38
     ഒന്ന
    0.38
     satu
    0.38
    Act Density 0.042%

    No Known Activations