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

    Neuronpedia

    INDEX
    Explanations

    module or DB installation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    INTRESOURCE
    1.31
    >{{
    1.13
     называют
    1.08
     впервые
    1.07
    ীতি
    1.07
     parede
    1.05
    醛
    1.04
     घोष
    1.04
    typicode
    1.03
     вопрос
    1.03
    POSITIVE LOGITS
    aac
    1.70
    ا
    1.63
    न
    1.61
    smanship
    1.60
    a
    1.57
    aabb
    1.52
    kaw
    1.42
    1.41
     Substituting
    1.41
    ﹟
    1.40
    Act Density 0.000%

    No Known Activations