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

    Neuronpedia

    INDEX
    Explanations

    uncensored

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    වාස
    0.88
    as
    0.84
    ഹ്ലാദ
    0.81
     thống
    0.81
    ീയ
    0.79
    일
    0.78
    લ્પ
    0.77
     handwriting
    0.77
    নাথ
    0.77
    на
    0.75
    POSITIVE LOGITS
     veren
    0.85
     ș
    0.81
    ة
    0.77
     rumoured
    0.76
    ры
    0.73
    eppo
    0.72
     Всё
    0.72
     ngựa
    0.70
     colect
    0.69
    го
    0.69
    Act Density 0.003%

    No Known Activations