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

    Neuronpedia

    INDEX
    Explanations

    assertEqual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     způsob
    0.92
     enzimas
    0.91
     decouple
    0.90
    Три
    0.88
    ضافة
    0.87
    Ги
    0.87
     foreseeable
    0.86
     hiçbir
    0.85
     twinkle
    0.84
     proteínas
    0.84
    POSITIVE LOGITS
    Built
    0.79
    er
    0.77
    heads
    0.73
    籍
    0.72
    τον
    0.72
    H
    0.71
     Homes
    0.71
     Outfit
    0.70
    TERS
    0.69
     Shri
    0.69
    Act Density 0.001%

    No Known Activations