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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wendungen
    -0.09
     થતા
    -0.08
    (course
    -0.08
     вина
    -0.08
    (alert
    -0.07
    (accounts
    -0.07
     cortes
    -0.07
     વ
    -0.07
     энергии
    -0.07
     absoluut
    -0.07
    POSITIVE LOGITS
    -Link
    0.08
    Ascii
    0.08
     والتر
    0.08
    /B
    0.08
    007
    0.08
     следующий
    0.07
     unfair
    0.07
     Billy
    0.07
     unjust
    0.07
     Porter
    0.07
    Act Density 0.001%

    No Known Activations