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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಹಾಗೂ
    0.80
     বেশকিছু
    0.63
     તથા
    0.61
     tzw
    0.56
    த்தினை
    0.55
    最为
    0.55
     vuol
    0.55
     ഏറെ
    0.55
    鉐
    0.55
     bowiem
    0.54
    POSITIVE LOGITS
     XNUMX
    0.75
     ​​
    0.75
    𝕜
    0.62
     verwendet
    0.58
     Anda
    0.57
     lütfen
    0.56
    ٪
    0.56
     você
    0.55
     นี่
    0.54
     möglicherweise
    0.53
    Act Density 0.000%

    No Known Activations