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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olis
    -0.07
     prevention
    -0.07
    pot
    -0.06
    conversion
    -0.06
    遣
    -0.06
     Bobby
    -0.06
     score
    -0.06
    obby
    -0.06
     ساز
    -0.06
    announcement
    -0.06
    POSITIVE LOGITS
     dashes
    0.07
     alla
    0.07
     Flex
    0.07
    tual
    0.06
    月
    0.06
     Leafs
    0.06
    (inertia
    0.06
     Dare
    0.06
    dbContext
    0.06
    azione
    0.06
    Act Density 0.266%

    No Known Activations