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

    Neuronpedia

    INDEX
    Explanations

    Windows 8.1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    0.61
    en
    0.56
    us
    0.55
     stipulates
    0.55
    et
    0.55
     effectuer
    0.54
     devraient
    0.54
     &
    0.53
    on
    0.53
     обосно
    0.53
    POSITIVE LOGITS
    这一切
    0.56
     Ngọc
    0.52
    这个
    0.50
    }"/>
    0.49
    مل
    0.48
     Гра
    0.48
     життя
    0.47
     Questa
    0.47
     ENERGY
    0.47
     Verónica
    0.47
    Act Density 0.116%

    No Known Activations