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

    Neuronpedia

    INDEX
    Explanations

    finding process ID

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Во
    0.48
    曌
    0.47
    ій
    0.46
    Мы
    0.46
    市場
    0.46
    Imagine
    0.46
    倛
    0.45
    Рас
    0.45
    Все
    0.44
    䀠
    0.44
    POSITIVE LOGITS
     deste
    0.45
     FB
    0.44
     requisite
    0.44
     rog
    0.43
     n
    0.43
     N
    0.43
     T
    0.42
     bł
    0.42
     II
    0.42
     väldigt
    0.41
    Act Density 0.004%

    No Known Activations