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

    Neuronpedia

    INDEX
    Explanations

    previously reported/described

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -us
    -0.07
     روان
    -0.06
    세
    -0.06
     Eis
    -0.06
     Carousel
    -0.06
    ΟΛ
    -0.06
     gab
    -0.06
    こそ
    -0.06
     HTTPS
    -0.06
    αρά
    -0.06
    POSITIVE LOGITS
     defines
    0.07
     suspense
    0.06
    -encoded
    0.06
    Unt
    0.06
    	Collection
    0.06
     getProduct
    0.06
     Definitely
    0.06
    <Expression
    0.06
     roi
    0.06
     ye
    0.06
    Act Density 0.006%

    No Known Activations