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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NumberOf
    -0.08
     verbose
    -0.07
     Loads
    -0.07
    [:,:
    -0.07
    arris
    -0.07
     Bearing
    -0.07
     famille
    -0.07
     сент
    -0.06
     monuments
    -0.06
    .after
    -0.06
    POSITIVE LOGITS
    寻
    0.07
     fj
    0.06
     IICIII
    0.06
     Gig
    0.06
    ịch
    0.06
     grabbing
    0.06
    currentIndex
    0.06
     дел
    0.06
    默
    0.06
    refix
    0.06
    Act Density 0.019%

    No Known Activations