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

    Neuronpedia

    INDEX
    Explanations

    the phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    out
    0.77
    ্যালেঞ্জ
    0.76
    тво
    0.65
    тся
    0.65
     творчества
    0.64
    CR
    0.64
    діть
    0.64
    鍔
    0.64
     &'
    0.63
    SCH
    0.63
    POSITIVE LOGITS
     nilpotent
    0.92
    ありません
    0.84
     chanted
    0.83
     businesswoman
    0.83
     fared
    0.80
    া
    0.79
    te
    0.78
    achlor
    0.77
    𝑎
    0.77
    なりません
    0.76
    Act Density 0.002%

    No Known Activations