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

    Neuronpedia

    INDEX
    Explanations

    hasta que

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    am
    1.53
    as
    1.25
    en
    1.19
    و
    1.09
    u
    1.07
    os
    1.06
    za
    1.04
    ot
    1.03
    on
    1.02
    us
    0.99
    POSITIVE LOGITS
    ки
    1.34
    ین
    1.24
     automóviles
    1.13
     evacu
    1.07
    िंग
    1.06
    ק
    1.05
    ۰
    1.05
    ة
    1.04
    ει
    1.03
    ক
    1.02
    Act Density 0.000%

    No Known Activations