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

    Neuronpedia

    INDEX
    Explanations

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toho
    1.69
     ĝi
    1.59
     dessen
    1.57
     ይህም
    1.53
    𝑠
    1.52
     এগুলো
    1.52
     těch
    1.51
     diberi
    1.51
    ுங்கள்
    1.51
     এটি
    1.50
    POSITIVE LOGITS
    これで
    1.97
    ۤ
    1.63
    あくまで
    1.47
    o
    1.46
    ga
    1.44
    রকম
    1.43
    guo
    1.41
     Spinal
    1.41
    gi
    1.38
    культур
    1.38
    Act Density 0.861%

    No Known Activations