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

    Neuronpedia

    INDEX
    Explanations

    has been/become/evolved/grown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻤ
    1.44
    ﺭ
    1.43
    ﻧ
    1.41
     Органи
    1.27
    ﺒ
    1.27
    ल्लिंग
    1.26
    abbanti
    1.24
     ollut
    1.22
     최근
    1.21
    enderung
    1.20
    POSITIVE LOGITS
     which
    1.62
     when
    1.55
     or
    1.52
     if
    1.52
     -
    1.48
    -
    1.43
     of
    1.38
     that
    1.33
     from
    1.29
     and
    1.27
    Act Density 0.000%

    No Known Activations