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

    Neuronpedia

    INDEX
    Explanations

    Linux, philosophical, boroughs, ankle booties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     =-\
    0.41
    ائی
    0.39
    ாவின்
    0.39
     Davis
    0.38
    時間は
    0.37
    Davis
    0.37
    Ƌ
    0.37
    ダス
    0.37
     DAVIS
    0.36
     dav
    0.36
    POSITIVE LOGITS
    Interesting
    0.41
    篇文章
    0.39
     Dign
    0.37
     makalah
    0.36
    nego
    0.36
    него
    0.36
     கட்டுர
    0.36
    মিস
    0.36
    尺
    0.35
     luces
    0.35
    Act Density 0.000%

    No Known Activations