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

    Neuronpedia

    INDEX
    Explanations

    security personnel systems and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    부터
    1.81
    ཝ
    1.76
    डी
    1.62
    时光
    1.62
    и
    1.60
    な
    1.59
    يد
    1.56
    한
    1.55
    ા
    1.49
    回事
    1.47
    POSITIVE LOGITS
    it
    1.73
    ik
    1.66
    ro
    1.57
     setTimeout
    1.49
     Inspect
    1.48
     enveloped
    1.48
     Eliminate
    1.45
    ли
    1.42
     hereby
    1.42
    us
    1.41
    Act Density 0.000%

    No Known Activations