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

    Neuronpedia

    INDEX
    Explanations

    non-english or multilingual contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    1.55
     \
    1.30
     for
    1.27
     T
    1.25
     M
    1.22
     A
    1.15
     P
    1.13
     L
    1.10
     E
    1.10
     N
    1.09
    POSITIVE LOGITS
    ல்
    1.45
    ко
    1.41
    ة
    1.09
    ской
    1.07
     сообщи
    1.05
     отмети
    1.05
     crece
    1.02
     destac
    1.02
    ний
    1.01
    anız
    1.01
    Act Density 0.329%

    No Known Activations