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

    Neuronpedia

    INDEX
    Explanations

    the expanse sci-fi series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caratteristiche
    0.53
    ίνη
    0.52
    肋
    0.50
    CAC
    0.48
     belt
    0.47
     klikken
    0.46
    fehlung
    0.46
    핑
    0.46
    ্্র
    0.46
     достат
    0.46
    POSITIVE LOGITS
    na
    0.57
    n
    0.57
    sq
    0.55
    m
    0.55
    students
    0.54
    u
    0.53
    metro
    0.52
    to
    0.52
    z
    0.52
    library
    0.50
    Act Density 0.000%

    No Known Activations