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

    Neuronpedia

    INDEX
    Explanations

    at the end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    0.18
     اکنون
    0.18
     Bây
    0.18
    same
    0.17
    ató
    0.17
    ஜி
    0.17
     tại
    0.17
     wł
    0.16
    Lr
    0.16
     graz
    0.16
    POSITIVE LOGITS
     конце
    0.26
     끝
    0.24
     конца
    0.23
    可怕
    0.21
    نامه
    0.21
     końca
    0.19
     end
    0.19
     koniec
    0.19
     досто
    0.19
     Dropbox
    0.19
    Act Density 0.033%

    No Known Activations