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

    Neuronpedia

    INDEX
    Explanations

    Standard deviation symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scott
    -0.07
    	user
    -0.07
    respect
    -0.06
     فرو
    -0.06
     admits
    -0.06
     arz
    -0.06
     outro
    -0.06
     عز
    -0.06
    řiv
    -0.06
    Provider
    -0.06
    POSITIVE LOGITS
    ื้
    0.07
    مول
    0.07
    pm
    0.07
     ±
    0.06
     hob
    0.06
    leurs
    0.06
     redeemed
    0.06
     муль
    0.06
    .'</
    0.06
    ´
    0.06
    Act Density 0.006%

    No Known Activations