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

    Neuronpedia

    INDEX
    Explanations

    said or says

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tilizer
    -1.53
    𝟵
    -1.43
     how
    -1.34
    煕
    -1.32
    ’
    -1.32
    と思いますが
    -1.31
     breakdowns
    -1.30
     welchen
    -1.29
    xcd
    -1.28
    碍
    -1.28
    POSITIVE LOGITS
     about
    1.77
    ܜ
    1.55
    :
    1.36
    他
    1.34
     by
    1.32
    月
    1.27
    約
    1.26
    لاً
    1.23
    kuš
    1.20
     pingente
    1.18
    Act Density 0.012%

    No Known Activations