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

    Neuronpedia

    INDEX
    Explanations

    ShareGPT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тесто
    0.40
    src
    0.39
     юбилей
    0.39
     чём
    0.38
     верхней
    0.38
    Ч
    0.37
     அமைக்க
    0.37
     amper
    0.37
    𒁀
    0.37
     cort
    0.36
    POSITIVE LOGITS
    Share
    0.70
     Share
    0.70
    share
    0.63
     share
    0.62
    holder
    0.59
    分享
    0.58
     Sharing
    0.58
    holders
    0.56
     SHARE
    0.56
    able
    0.51
    Act Density 0.009%

    No Known Activations