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

    Neuronpedia

    INDEX
    Explanations

    exclusive offers and access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    1.27
    س
    1.21
    이었
    1.08
     않았
    0.98
    ,!
    0.96
    It
    0.93
    الأ
    0.93
    As
    0.93
     받았
    0.93
    }^
    0.92
    POSITIVE LOGITS
     exclusive
    1.51
     exclusivity
    1.41
    i
    1.29
     exclusivo
    1.23
    exclusive
    1.17
     exclusiva
    1.15
    ur
    1.14
     Exclusive
    1.13
     exclusives
    1.07
     exclusively
    1.05
    Act Density 0.003%

    No Known Activations