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

    Neuronpedia

    INDEX
    Explanations

    Premier League

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.35
    of
    1.02
    は
    1.01
    는
    0.98
    0.91
    은
    0.88
    是
    0.84
    e
    0.80
    AM
    0.79
    た
    0.79
    POSITIVE LOGITS
    л
    0.86
    ر
    0.81
    ۰
    0.66
    ០
    0.66
    嶈
    0.64
    рия
    0.63
     её
    0.63
     ребён
    0.62
    لية
    0.60
     polymeric
    0.60
    Act Density 0.001%

    No Known Activations