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

    Neuronpedia

    INDEX
    Explanations

    section headings and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ៖
    0.28
    未來
    0.26
     toekom
    0.23
    Còn
    0.23
    महिलाओं
    0.22
    নতুন
    0.22
    おすすめです
    0.22
    MANAGER
    0.22
    :";
    0.22
     தவிர்க்க
    0.22
    POSITIVE LOGITS
     of
    0.26
    ofthe
    0.25
     inasmuch
    0.23
     and
    0.23
     overview
    0.22
     ofthe
    0.22
     della
    0.21
     एवं
    0.21
     there
    0.21
    /@
    0.21
    Act Density 0.521%

    No Known Activations