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

    Neuronpedia

    INDEX
    Explanations

    yang followed by adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    1.30
    of
    1.26
    ли
    1.23
    ar
    1.20
    است
    1.20
    ра
    1.13
    ↵↵
    1.11
    er
    1.11
    ма
    1.10
    ες
    1.10
    POSITIVE LOGITS
     yang
    1.38
     ที่
    1.20
     molto
    1.16
     yanı
    1.15
     が
    1.13
     jeste
    1.13
    y
    1.12
     frumo
    1.10
     salari
    1.09
     been
    1.09
    Act Density 0.000%

    No Known Activations