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

    Neuronpedia

    INDEX
    Explanations

    clear the surface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     figure
    0.37
    цтва
    0.37
    figure
    0.36
     cart
    0.36
     kindle
    0.35
    chende
    0.34
    backers
    0.34
     he
    0.33
     participants
    0.33
     Aufmerksamkeit
    0.33
    POSITIVE LOGITS
    新闻
    0.58
    गिन
    0.54
    新聞
    0.50
     berita
    0.50
     뉴스
    0.48
    邮
    0.47
     noticias
    0.47
     exceso
    0.46
    ニュース
    0.46
    辉
    0.46
    Act Density 0.000%

    No Known Activations