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

    Neuronpedia

    INDEX
    Explanations

    specific conditions or contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     semua
    1.24
     všetky
    1.23
     todas
    1.18
    all
    1.18
    所有
    1.18
     all
    1.17
     جميع
    1.17
     усіх
    1.14
     wszystkie
    1.12
     svih
    1.11
    POSITIVE LOGITS
    或是
    0.74
     或者
    0.72
    setFooter
    0.71
    塾
    0.67
     сайт
    0.67
     либо
    0.67
     reset
    0.66
     리뷰
    0.65
     행사
    0.65
    ர்கள்
    0.64
    Act Density 0.268%

    No Known Activations