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

    Neuronpedia

    INDEX
    Explanations

    URSS, Almorox

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ek
    1.52
    ــــ
    1.46
    ﺮ
    1.46
    ــــــــ
    1.45
    ური
    1.45
    ـــ
    1.44
    ــ
    1.40
    eb
    1.40
    yrs
    1.38
    es
    1.35
    POSITIVE LOGITS
    رر
    1.61
    rrrr
    1.52
    hythm
    1.49
    hythmic
    1.45
    incipal
    1.41
    णीय
    1.39
    rrr
    1.33
    োহণ
    1.29
    fahrung
    1.28
    ﻩ
    1.23
    Act Density 0.796%

    No Known Activations