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

    Neuronpedia

    INDEX
    Explanations

    apply to you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    所の
    0.45
     우리가
    0.42
     تكونوا
    0.42
     meine
    0.41
     நாம்
    0.41
    私が
    0.41
     తాను
    0.40
     কয়েকজন
    0.40
    자들이
    0.39
     своим
    0.39
    POSITIVE LOGITS
     iā
    0.62
     عليك
    0.51
     عليه
    0.48
     ಅವ
    0.47
    你了
    0.44
     उनसे
    0.44
     ним
    0.43
     إليه
    0.42
     देम
    0.42
     منك
    0.41
    Act Density 0.023%

    No Known Activations