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

    Neuronpedia

    INDEX
    Explanations

    is adjective

    np_acts-logits-general · gemini-2.5-flash-lite

    is significant, beyond, lower

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.68
    (
    0.63
    *
    0.61
     in
    0.61
    在
    0.61
    ?
    0.59
    >
    0.51
    [
    0.49
    #
    0.49
    (.*
    0.48
    POSITIVE LOGITS
    d
    0.65
    dır
    0.54
     is
    0.52
    dı
    0.52
    larında
    0.51
    larını
    0.50
    u
    0.50
    いた
    0.50
    もの
    0.50
    dj
    0.50
    Act Density 1.119%

    No Known Activations