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

    Neuronpedia

    INDEX
    Explanations

    professional certification or process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    1.24
     ﺍﻟ
    1.12
    ન
    1.10
    ﻪ
    1.09
    ﻨ
    1.08
    ﯽ
    1.07
    ﻱ
    1.04
     conex
    1.02
     فونبټ
    1.02
     visione
    1.01
    POSITIVE LOGITS
    is
    1.34
    0
    1.31
    and
    1.23
    ar
    1.15
    ok
    1.14
    are
    1.14
    <0x80>
    1.09
    an
    1.09
    Certified
    1.02
    certification
    1.01
    Act Density 0.003%

    No Known Activations