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

    Neuronpedia

    INDEX
    Explanations

    key improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鑰
    0.43
    キー
    0.43
     KEYS
    0.41
    겠지만
    0.41
    key
    0.40
    KEY
    0.40
    KEYS
    0.40
    键
    0.39
    erà
    0.38
    鍵
    0.38
    POSITIVE LOGITS
     explica
    0.43
     explains
    0.40
     bur
    0.39
     points
    0.38
     पू
    0.38
     highlights
    0.38
     объяс
    0.38
     aspects
    0.38
     salary
    0.38
    movieId
    0.38
    Act Density 0.007%

    No Known Activations