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

    Neuronpedia

    INDEX
    Explanations

    programming libraries and modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    荷兰
    0.43
    Ｙ
    0.41
    alpine
    0.41
    absence
    0.40
    kar
    0.40
    esterno
    0.40
    width
    0.40
    avac
    0.40
    াণ
    0.40
    Dylan
    0.39
    POSITIVE LOGITS
     produtos
    0.48
     Produkte
    0.46
    库
    0.45
     prodotti
    0.44
     produkty
    0.44
    製品
    0.43
    Primitives
    0.43
     produkter
    0.43
    Products
    0.42
     Productos
    0.42
    Act Density 0.150%

    No Known Activations