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

    Neuronpedia

    INDEX
    Explanations

    multilingual language particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kalau
    1.21
     iedere
    1.21
     forcément
    1.14
    オシャレ
    1.10
     Lietuvos
    1.09
     inox
    1.08
    這邊
    1.07
     kalau
    1.06
     bisogna
    1.05
     अफसरों
    1.03
    POSITIVE LOGITS
    および
    0.84
     ​​
    0.83
    または
    0.67
    潜在
    0.66
     XNUMX
    0.59
     чрезвы
    0.59
     লোকেরা
    0.58
    旨在
    0.57
    십시오
    0.57
    可用
    0.55
    Act Density 0.068%

    No Known Activations