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

    Neuronpedia

    INDEX
    Explanations

    stabilized, -ization endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    2.27
    t
    2.17
    d
    2.03
    de
    1.41
    p
    1.38
    <0x0D>
    1.37
    ll
    1.34
    main
    1.30
     of
    1.27
    m
    1.26
    POSITIVE LOGITS
    л
    1.38
    ро
    1.36
    ू
    1.35
    و
    1.22
    us
    1.20
    ва
    1.18
    са
    1.13
    ط
    1.13
    ี
    1.10
    σιμοποι
    1.09
    Act Density 0.000%

    No Known Activations