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

    Neuronpedia

    INDEX
    Explanations

    have no or have a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.47
    чи
    0.40
     في
    0.37
    ла
    0.37
    тта
    0.36
     adhipp
    0.35
     bicovariant
    0.35
     ಒಳಗ
    0.34
     imasmim
    0.34
    人了
    0.34
    POSITIVE LOGITS
     on
    0.53
     of
    0.52
    h
    0.44
    \
    0.43
     Have
    0.42
    0.40
    ä
    0.39
    >
    0.38
     On
    0.38
    A
    0.38
    Act Density 0.298%

    No Known Activations