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

    Neuronpedia

    INDEX
    Explanations

    categories and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mesmos
    0.46
    即使
    0.45
     avancé
    0.44
     elucidated
    0.44
     CONDITIONS
    0.43
     unveiled
    0.42
     пом
    0.42
     оригинала
    0.41
    icale
    0.41
     режима
    0.41
    POSITIVE LOGITS
    y
    0.64
    g
    0.51
    o
    0.51
    u
    0.51
    is
    0.50
    X
    0.50
    x
    0.49
    k
    0.49
    and
    0.48
    LL
    0.48
    Act Density 0.003%

    No Known Activations