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

    Neuronpedia

    INDEX
    Explanations

    who is doing what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ஆகியவற்ற
    0.35
     ஆகியவை
    0.34
    觉
    0.34
     συνε
    0.34
    坛
    0.32
    鬯
    0.32
    бва
    0.31
    ொள்
    0.31
    ஷ
    0.31
    떨
    0.31
    POSITIVE LOGITS
     who
    3.42
     Who
    3.17
    who
    3.17
    Who
    3.08
    谁
    2.97
     quien
    2.92
    誰
    2.91
     quién
    2.89
     кто
    2.70
     siapa
    2.69
    Act Density 0.030%

    No Known Activations