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

    Neuronpedia

    INDEX
    Explanations

    Milky Way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    1.38
    t
    1.28
     to
    1.26
    ン
    1.21
     a
    1.18
    A
    1.13
    im
    1.11
    int
    1.11
    in
    1.01
    to
    1.01
    POSITIVE LOGITS
    лы
    1.22
    ер
    1.11
    є
    0.96
    も含
    0.95
    0.95
     dangereux
    0.92
     없다
    0.92
    ри
    0.90
    рити
    0.89
    દ
    0.89
    Act Density 0.000%

    No Known Activations