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

    Neuronpedia

    INDEX
    Explanations

    many or some

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    三次
    0.71
     zweimal
    0.62
     twice
    0.61
    engkapi
    0.60
     সংক্রান্ত
    0.59
    一共
    0.59
     birbir
    0.59
     threefold
    0.59
    zęd
    0.59
    twice
    0.58
    POSITIVE LOGITS
     many
    3.95
     some
    3.77
     Many
    3.66
    Many
    3.64
     muitos
    3.61
     Some
    3.58
    Some
    3.58
     algunos
    3.54
     многие
    3.54
    many
    3.50
    Act Density 0.758%

    No Known Activations