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

    Neuronpedia

    INDEX
    Explanations

    meme generator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    1.31
    in
    1.09
    y
    1.08
    as
    1.03
    at
    0.98
    ing
    0.97
    am
    0.97
    I
    0.94
    an
    0.92
    A
    0.91
    POSITIVE LOGITS
     öner
    0.89
     otev
    0.88
     ouvertes
    0.86
    ри
    0.82
     meme
    0.82
     oude
    0.79
     özel
    0.79
     apie
    0.79
     adı
    0.79
     étoiles
    0.78
    Act Density 0.005%

    No Known Activations