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

    Neuronpedia

    INDEX
    Explanations

    statistics and Xinhua

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কৃত
    0.41
    0.40
    銳
    0.40
    Multipart
    0.40
     पुण्य
    0.39
    দ্‌
    0.37
    დნენ
    0.36
    Hourly
    0.36
    மாவட்ட
    0.36
    ിയത്
    0.36
    POSITIVE LOGITS
     Xinhua
    0.54
     x
    0.45
    x
    0.44
    Xinhua
    0.41
    𝑥
    0.41
    Chooser
    0.41
     х
    0.39
    CHO
    0.38
    xxxxxxxx
    0.38
    xx
    0.37
    Act Density 0.000%

    No Known Activations