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

    Neuronpedia

    INDEX
    Explanations

    saponins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multer
    -0.07
    	RTE
    -0.07
    績
    -0.06
     Cambodia
    -0.06
    ليف
    -0.06
    Sold
    -0.06
    ██
    -0.06
     tys
    -0.06
    лев
    -0.06
    =}
    -0.06
    POSITIVE LOGITS
    apon
    0.07
     scape
    0.06
    니다
    0.06
    apsulation
    0.06
     señ
    0.06
     nowadays
    0.06
     mismo
    0.06
     sám
    0.06
     мой
    0.06
    マ
    0.06
    Act Density 0.001%

    No Known Activations