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

    Neuronpedia

    INDEX
    Explanations

    Classification, tables, competitive advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ের
    0.62
    ים
    0.58
    s
    0.55
    ,
    0.54
     winner
    0.50
    ی
    0.50
    ਆਂ
    0.49
     {
    0.48
    ่า
    0.47
     F
    0.47
    POSITIVE LOGITS
    Тех
    0.57
    Although
    0.52
    Это
    0.50
    This
    0.49
    ইউনি
    0.49
    が通販
    0.48
    for
    0.48
    Пред
    0.48
    0.48
     تف
    0.47
    Act Density 0.001%

    No Known Activations