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

    Neuronpedia

    INDEX
    Explanations

    formulaic units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䐍
    0.46
    đer
    0.44
    expensive
    0.44
    ྥ
    0.43
     বেল
    0.43
    ・・・・
    0.42
    姮
    0.42
    odhya
    0.41
    imoto
    0.41
     ふ
    0.40
    POSITIVE LOGITS
    /
    0.39
    lio
    0.39
    :
    0.38
     signific
    0.38
     संजीव
    0.38
    GREES
    0.38
     laure
    0.38
     tradu
    0.36
    丵
    0.36
     کارت
    0.36
    Act Density 0.000%

    No Known Activations