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

    Neuronpedia

    INDEX
    Explanations

    indicating source after "according to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atteint
    1.20
    1.11
     mít
    1.08
     записи
    1.05
     successivo
    0.98
     partielle
    0.95
     WHILE
    0.93
     создание
    0.91
    ').
    0.90
     هناك
    0.89
    POSITIVE LOGITS
    3
    1.64
    is
    1.30
    6
    1.30
    the
    1.23
    7
    1.23
    os
    1.22
    4
    1.20
    τή
    1.19
    it
    1.14
    ro
    1.11
    Act Density 0.029%

    No Known Activations