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

    Neuronpedia

    INDEX
    Explanations

    lead actions and teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.99
    t
    0.84
     to
    0.77
    w
    0.72
    R
    0.70
    l
    0.68
     законом
    0.63
    d
    0.62
    s
    0.61
    S
    0.61
    POSITIVE LOGITS
    ни
    0.71
    ності
    0.61
     unsere
    0.59
    ِينَ
    0.59
     Gospod
    0.58
    くな
    0.57
    يم
    0.57
    ыз
    0.57
    asiti
    0.56
    يمان
    0.56
    Act Density 0.002%

    No Known Activations