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

    Neuronpedia

    INDEX
    Explanations

    prolific artists and works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onboarding
    0.47
    当下
    0.41
    必要があります
    0.41
     WeChat
    0.40
    💡
    0.39
    スマホ
    0.39
     unintended
    0.39
     momentary
    0.39
     Canva
    0.39
     потребуется
    0.39
    POSITIVE LOGITS
     работал
    0.60
     principalmente
    0.59
     specialising
    0.59
     주로
    0.59
     prolific
    0.58
     తన
    0.57
     hauptsächlich
    0.57
     principalement
    0.56
    主に
    0.56
     głównie
    0.55
    Act Density 0.112%

    No Known Activations