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

    Neuronpedia

    INDEX
    Explanations

    in vitro, drug, type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yiz
    1.05
    которые
    1.04
    обходимо
    1.02
     pochod
    1.01
    Ფ
    1.01
     sprawy
    0.99
    alış
    0.97
    ০০
    0.96
     badass
    0.95
     εδώ
    0.95
    POSITIVE LOGITS
    页面存档备份
    1.85
    cknowled
    1.45
     $^{\
    1.40
    ຳ
    1.37
    此之外
    1.37
    री
    1.30
     $_{
    1.28
     $^{
    1.27
     $_{\
    1.25
    특별시
    1.24
    Act Density 0.291%

    No Known Activations