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

    Neuronpedia

    INDEX
    Explanations

    proper name beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কিছু
    0.29
     অল্প
    0.27
    ستگی
    0.27
    İR
    0.26
     तिलावत
    0.26
    整个
    0.26
     Sự
    0.26
    魉
    0.26
     كما
    0.26
    Í
    0.26
    POSITIVE LOGITS
    훈
    0.27
     projektu
    0.26
     réessayer
    0.26
     conductas
    0.26
     benutzt
    0.25
    पृ
    0.25
     लेगा
    0.25
    barui
    0.24
     deport
    0.24
    ؤال
    0.24
    Act Density 0.494%

    No Known Activations