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

    Neuronpedia

    INDEX
    Explanations

    help of

    np_acts-logits-general · gemini-2.5-flash-lite

    context, fact, or dealing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ру
    1.08
     поколения
    0.92
    ре
    0.92
     wèi
    0.89
     ಕ್ಷೇತ್ರ
    0.86
     വഴി
    0.85
     контроль
    0.84
     আশে
    0.84
     роботу
    0.84
     город
    0.83
    POSITIVE LOGITS
    of
    1.28
     of
    1.23
    t
    1.12
    is
    1.09
    Α
    1.07
    (
    0.93
    K
    0.93
    el
    0.89
    '
    0.89
    y
    0.87
    Act Density 3.223%

    No Known Activations