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

    Neuronpedia

    INDEX
    Explanations

    html lang attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    igslist
    0.39
     Cunningham
    0.38
    فا
    0.37
     فا
    0.37
    Mileage
    0.37
    萝
    0.37
    atchewan
    0.36
    기로
    0.36
     Lonely
    0.36
     Sied
    0.36
    POSITIVE LOGITS
     lang
    0.65
    lang
    0.64
     LANG
    0.46
    Lang
    0.46
     Lang
    0.45
    언
    0.45
     언
    0.43
     idioma
    0.43
     jazy
    0.42
    郎
    0.42
    Act Density 0.003%

    No Known Activations