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

    Neuronpedia

    INDEX
    Explanations

    applies to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    1.13
    4
    1.11
    .
    1.05
    3
    1.03
    5
    1.00
    6
    0.93
    7
    0.87
    (
    0.83
    9
    0.76
    ä
    0.73
    POSITIVE LOGITS
    u
    1.09
    k
    1.02
     aliments
    0.95
    n
    0.87
    kowe
    0.84
     esenciales
    0.82
    kf
    0.82
    m
    0.81
    kho
    0.81
    ق
    0.81
    Act Density 0.000%

    No Known Activations