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

    Neuronpedia

    INDEX
    Explanations

    Singlish and Chinese internet slang

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    縝
    0.62
    蓍
    0.58
    Analysis
    0.57
    ليل
    0.57
    濰
    0.57
    頜
    0.57
     фаразы
    0.55
    栻
    0.55
    銑
    0.55
    Produto
    0.54
    POSITIVE LOGITS
    0.66
    !
    0.62
     banget
    0.61
    ！
    0.59
    吃
    0.58
     galore
    0.57
     😂
    0.54
     !
    0.54
     k
    0.54
     bang
    0.54
    Act Density 0.014%

    No Known Activations