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

    Neuronpedia

    INDEX
    Explanations

    bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    纷纷
    -0.08
     Pedido
    -0.07
     국민
    -0.07
    при
    -0.07
    то
    -0.07
    ozy
    -0.07
    dé
    -0.07
    amiliar
    -0.07
    比如说
    -0.07
     tricks
    -0.07
    POSITIVE LOGITS
    早餐加盟
    0.07
    odial
    0.07
    CollectionView
    0.07
    ɂ
    0.07
    .globalData
    0.07
    🛡
    0.07
     yol
    0.07
    -connected
    0.07
    MLE
    0.06
    Ḫ
    0.06
    Act Density 0.089%

    No Known Activations