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

    Neuronpedia

    INDEX
    Explanations

    arc de triomphe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kä
    0.64
    Artwork
    0.63
    ках
    0.62
    hö
    0.62
    kT
    0.61
     Airbus
    0.61
    m
    0.61
    zah
    0.60
     a
    0.59
    cells
    0.58
    POSITIVE LOGITS
     waiter
    0.60
     ragazzo
    0.59
     fiery
    0.58
    ла
    0.57
    لا
    0.56
    પણે
    0.55
    ولا
    0.55
    日在
    0.54
    ים
    0.53
    荣耀
    0.52
    Act Density 0.002%

    No Known Activations