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

    Neuronpedia

    INDEX
    Explanations

    official or formal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मतदारसं
    0.67
    य़
    0.62
     गुणों
    0.61
     ጠ
    0.60
     phù
    0.60
     사랑
    0.60
     ইতো
    0.59
     تعالى
    0.59
    ავს
    0.59
     जुटा
    0.59
    POSITIVE LOGITS
     official
    5.24
     Official
    4.81
    Official
    4.71
    official
    4.65
     officially
    4.55
     официа
    4.40
     oficial
    4.35
     offizi
    4.23
     OFFICIAL
    4.14
    官方
    4.13
    Act Density 0.465%

    No Known Activations