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

    Neuronpedia

    INDEX
    Explanations

    the verge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    1.20
    0
    1.08
     are
    0.86
     طريق
    0.83
     for
    0.82
     ב
    0.78
     not
    0.77
    يف
    0.76
     by
    0.75
    在
    0.75
    POSITIVE LOGITS
    u
    0.83
    های
    0.80
    ्यु
    0.75
    ری
    0.70
    atthanam
    0.70
    ਾ
    0.70
    ede
    0.68
    znego
    0.68
    akaranam
    0.68
    लट्
    0.68
    Act Density 0.000%

    No Known Activations