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

    Neuronpedia

    INDEX
    Explanations

    already and its context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    多い
    1.19
    お子
    1.15
    お届け
    1.05
     불구하고
    1.02
    お
    0.97
    々は
    0.97
    おそらく
    0.94
    Վ
    0.94
    メガネ
    0.93
    你
    0.93
    POSITIVE LOGITS
    ات
    1.41
    ي
    1.23
    '
    1.12
    i
    1.02
    en
    1.00
    ro
    0.96
    da
    0.94
    는
    0.94
    der
    0.89
    I
    0.89
    Act Density 0.004%

    No Known Activations