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

    Neuronpedia

    INDEX
    Explanations

    language identification and difficulty levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    0.42
     Armenian
    0.41
    curs
    0.38
     mé
    0.36
     /
    0.35
    加えて
    0.35
    ,-
    0.35
    Ս
    0.35
    ரி
    0.35
     compl
    0.35
    POSITIVE LOGITS
    يمان
    0.42
     እንዴት
    0.41
     स्त्रीलिंग
    0.40
    how
    0.39
     ಎಷ್ಟು
    0.37
    వా
    0.37
    何
    0.37
     повин
    0.37
    procedures
    0.37
    陘
    0.36
    Act Density 0.000%

    No Known Activations