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

    Neuronpedia

    INDEX
    Explanations

    expand and spread

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CI
    2.68
    inib
    2.60
    isPlaying
    2.52
    មី
    2.43
    Pairs
    2.42
    ્વ
    2.41
    istor
    2.39
    री
    2.39
     lå
    2.38
     Объ
    2.38
    POSITIVE LOGITS
    دق
    2.93
    ਦ
    2.71
    }{(
    2.52
    다
    2.51
    ulates
    2.50
    iential
    2.47
    ertain
    2.46
    iencing
    2.43
    htë
    2.42
     put
    2.39
    Act Density 0.632%

    No Known Activations