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

    Neuronpedia

    INDEX
    Explanations

    keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    шість
    0.39
     ਸਰ
    0.39
    ТЕ
    0.38
    閭
    0.38
    beiten
    0.37
    導數
    0.37
    葡
    0.37
    ashita
    0.37
    競争
    0.37
     Dham
    0.36
    POSITIVE LOGITS
     Keyword
    0.65
     keyword
    0.64
     Keywords
    0.59
    Keyword
    0.59
    keywords
    0.59
     keywords
    0.57
    关键字
    0.57
    keyword
    0.56
    Keywords
    0.54
    キーワード
    0.49
    Act Density 0.000%

    No Known Activations