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

    Neuronpedia

    INDEX
    Explanations

    children and early education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.74
    H
    0.73
    J
    0.67
    oria
    0.56
    He
    0.55
     offerte
    0.55
     jukebox
    0.55
     menswear
    0.54
     he
    0.53
     uk
    0.53
    POSITIVE LOGITS
     الأطفال
    1.34
     儿童
    1.27
     kinderen
    1.23
    👶
    1.23
     дошко
    1.22
     어린이
    1.17
     çocuk
    1.16
    幼儿
    1.15
    儿童
    1.13
     gyermek
    1.13
    Act Density 0.316%

    No Known Activations