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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ิว
    0.44
     coverage
    0.43
    ഘോഷ
    0.41
     flow
    0.41
     скорость
    0.41
    の効果
    0.40
    利用者
    0.40
     графи
    0.39
     phong
    0.39
     worshippers
    0.39
    POSITIVE LOGITS
     where
    0.51
     hvor
    0.50
     donde
    0.45
     где
    0.44
     gdzie
    0.41
    where
    0.40
     gdje
    0.39
     où
    0.39
     že
    0.38
     dónde
    0.38
    Act Density 0.006%

    No Known Activations