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

    Neuronpedia

    INDEX
    Explanations

    news and fake news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বইটি
    0.37
    ભ્ય
    0.37
    ܦ
    0.37
     ሂደ
    0.36
    棤
    0.36
     ರಚ
    0.35
     thisTrial
    0.35
     പരിച
    0.35
    স্‌
    0.35
    徃
    0.35
    POSITIVE LOGITS
     news
    4.22
    news
    3.78
     News
    3.67
    News
    3.63
    ニュース
    3.45
    新闻
    3.34
     NEWS
    3.27
     뉴스
    3.17
     noticias
    3.14
     nieuws
    3.11
    Act Density 0.085%

    No Known Activations