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

    Neuronpedia

    INDEX
    Explanations

    provide instructions or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ند
    1.03
     as
    1.01
    لي
    0.97
     hvilket
    0.96
     但是
    0.93
     الص
    0.92
    يد
    0.92
    ³.
    0.89
    ९
    0.89
    mu
    0.89
    POSITIVE LOGITS
    T
    1.99
    K
    1.78
    M
    1.75
    G
    1.73
    V
    1.67
    D
    1.58
    ב
    1.55
    W
    1.53
    R
    1.52
    H
    1.51
    Act Density 0.145%

    No Known Activations