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

    Neuronpedia

    INDEX
    Explanations

    lush and musk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.09
    ing
    0.88
    c
    0.85
    h
    0.84
    t
    0.82
    ad
    0.77
    m
    0.71
    tart
    0.70
    k
    0.70
    the
    0.68
    POSITIVE LOGITS
    с
    0.75
    ని
    0.69
     problemática
    0.66
     indicadores
    0.64
     přímo
    0.63
    ដែលមាន
    0.63
     LOTRAchievement
    0.62
    ۳
    0.62
     neće
    0.62
     tohoto
    0.61
    Act Density 0.001%

    No Known Activations