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

    Neuronpedia

    INDEX
    Explanations

    how to use or express gratitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sonian
    1.40
    skiy
    1.39
    蜴
    1.31
    nji
    1.31
    nın
    1.30
    ⺈
    1.28
    ῷ
    1.28
    nW
    1.26
    Ûn
    1.20
    शनी
    1.19
    POSITIVE LOGITS
     المر
    1.12
     rapport
    1.09
    pkt
    1.04
    投诉
    1.03
    技巧
    1.03
     Swimming
    1.01
     elementType
    1.01
    IFF
    0.99
    lets
    0.98
     swimming
    0.97
    Act Density 0.001%

    No Known Activations