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

    Neuronpedia

    INDEX
    Explanations

    list items and parenthetical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.89
    (
    0.84
     （
    0.81
     ();
    0.63
    （
    0.62
     }(\
    0.60
     ('
    0.59
     (“
    0.57
     ("",
    0.55
     ((
    0.54
    POSITIVE LOGITS
    a
    0.71
    ı
    0.67
    u
    0.58
    ):
    0.56
    z
    0.53
    et
    0.52
    e
    0.52
    ec
    0.52
    ում
    0.51
    ை
    0.51
    Act Density 0.725%

    No Known Activations