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

    Neuronpedia

    INDEX
    Explanations

    Singlish particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发布
    0.47
     continual
    0.43
     identifying
    0.41
     producing
    0.40
    Kir
    0.40
    ◊
    0.40
     offering
    0.40
     displacing
    0.40
     equ
    0.39
    0.39
    POSITIVE LOGITS
     kinda
    0.69
     somehow
    0.64
     artistes
    0.57
     sorta
    0.56
     Somehow
    0.56
     Datuk
    0.55
     stuffs
    0.55
     kampung
    0.52
     memang
    0.51
     artiste
    0.51
    Act Density 0.003%

    No Known Activations