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

    Neuronpedia

    INDEX
    Explanations

    Duplicate, Vk, chips, look, include, Mechanical, physically, Port

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ных
    1.62
    ीकृत
    1.41
    ায়
    1.38
    ৬৫
    1.31
    но
    1.26
    мента
    1.23
     carotid
    1.23
     sommige
    1.20
    ीन
    1.20
    પણે
    1.20
    POSITIVE LOGITS
    le
    1.49
    m
    1.47
    j
    1.47
    ，
    1.42
    ada
    1.41
    i
    1.38
    lidir
    1.35
    ing
    1.30
    li
    1.30
     I
    1.28
    Act Density 0.001%

    No Known Activations