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

    Neuronpedia

    INDEX
    Explanations

    what is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ქვენ
    0.49
     piernas
    0.46
    tochy
    0.46
    吺
    0.44
     जीते
    0.43
     पाण्यात
    0.43
     삽니다
    0.43
     नों
    0.43
    洴
    0.42
     heridas
    0.42
    POSITIVE LOGITS
     a
    0.77
     an
    0.70
     একটি
    0.62
     the
    0.59
     called
    0.54
     what
    0.53
     is
    0.50
     digital
    0.49
     '
    0.48
    Arithmetic
    0.48
    Act Density 0.080%

    No Known Activations