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

    Neuronpedia

    INDEX
    Explanations

    general or basic product concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     기
    0.50
     Display
    0.45
     W
    0.45
     완
    0.44
     전체
    0.44
     opis
    0.43
     Pro
    0.42
     Displays
    0.42
     Cards
    0.42
     Specifically
    0.42
    POSITIVE LOGITS
    mixing
    0.46
    problem
    0.45
    imbangan
    0.45
    生育
    0.44
    resistant
    0.43
    Rồi
    0.43
    mäßig
    0.43
     tradeoffs
    0.43
    congestion
    0.43
    龶
    0.43
    Act Density 0.012%

    No Known Activations