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

    Neuronpedia

    INDEX
    Explanations

    words starting with wh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.56
    et
    1.42
     for
    1.38
    н
    1.38
    م
    1.30
    ق
    1.19
     was
    1.16
    is
    1.11
    il
    1.08
    การ
    1.03
    POSITIVE LOGITS
    на
    1.33
    לו
    1.29
    ıyla
    1.19
    ếu
    1.17
    ми
    1.13
    ﻞ
    1.13
    ри
    1.13
    lüğ
    1.12
    ków
    1.08
    that
    1.07
    Act Density 0.016%

    No Known Activations