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

    Neuronpedia

    INDEX
    Explanations

    performance and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Im
    0.49
    롤
    0.48
     unclean
    0.47
    مسه
    0.47
    મિક
    0.47
    ्रिक
    0.45
    মাত
    0.45
     গুণ
    0.45
    柔
    0.45
     حی
    0.45
    POSITIVE LOGITS
    Notes
    0.51
     Народ
    0.50
    u
    0.48
    er
    0.46
     awaken
    0.45
    Passion
    0.45
    Strong
    0.45
    Iterator
    0.45
    Buzz
    0.44
    Campaign
    0.44
    Act Density 0.002%

    No Known Activations