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

    Neuronpedia

    INDEX
    Explanations

    a complex or significant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    1.23
    the
    1.05
    to
    1.03
    o
    0.94
    z
    0.91
    cence
    0.89
    по
    0.88
    و
    0.86
    b
    0.86
    se
    0.86
    POSITIVE LOGITS
    ﺔ
    0.86
     然而
    0.84
     Međutim
    0.82
     تاہم
    0.78
     Использу
    0.78
     那麼
    0.76
     Именно
    0.75
    然而
    0.75
     čini
    0.75
     Однако
    0.75
    Act Density 1.653%

    No Known Activations