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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bakanlığı
    -0.07
    还真是
    -0.07
     emploi
    -0.07
    硕
    -0.07
     minister
    -0.07
    作为一名
    -0.06
     sổ
    -0.06
    Docs
    -0.06
     księg
    -0.06
    泫
    -0.06
    POSITIVE LOGITS
    州区
    0.08
    	User
    0.07
    詈
    0.07
    venues
    0.07
    𣲘
    0.07
    眼光
    0.07
     требования
    0.07
     Ver
    0.06
    าน
    0.06
     doubly
    0.06
    Act Density 0.054%

    No Known Activations