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

    Neuronpedia

    INDEX
    Explanations

    during training or inference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    1.64
    m
    1.55
    l
    1.50
    c
    1.45
    il
    1.41
    не
    1.37
    al
    1.36
    en
    1.32
    8
    1.30
    ни
    1.29
    POSITIVE LOGITS
     وبعد
    1.49
    에는
    1.26
    BeerItem
    1.25
    ពេល
    1.12
    이나
    1.08
     וכ
    1.06
    이었
    1.03
     διάρκεια
    1.03
    larının
    1.02
     никто
    1.02
    Act Density 0.114%

    No Known Activations