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

    Neuronpedia

    INDEX
    Explanations

    my pre-existing knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ків
    0.48
    ين
    0.45
    氢
    0.45
     wn
    0.44
     raffle
    0.44
    ıt
    0.44
     diing
    0.43
    Initialization
    0.43
    гід
    0.42
     dyd
    0.42
    POSITIVE LOGITS
     on
    0.53
    ":
    0.46
     Romano
    0.46
     trailers
    0.43
    のリ
    0.42
     Manitoba
    0.41
     Cuthbert
    0.41
    짜
    0.40
    Somos
    0.40
    なら
    0.40
    Act Density 0.046%

    No Known Activations