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

    Neuronpedia

    INDEX
    Explanations

    there are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কে
    1.20
     aquilo
    1.05
    に近い
    1.05
    에
    1.03
    Y
    1.02
    ay
    1.01
     dement
    0.98
    に向け
    0.89
    iket
    0.89
    ä
    0.88
    POSITIVE LOGITS
    nymi
    1.36
    ﻞ
    1.25
    sion
    1.23
    ितीय
    1.21
    ्स
    1.15
    ูนย์
    1.15
    s
    1.13
    ný
    1.09
     discrepancies
    1.09
    আরো
    1.09
    Act Density 0.186%

    No Known Activations