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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Duel
    -0.07
    卷
    -0.07
    Defined
    -0.07
    尚
    -0.07
    Map
    -0.07
    沒
    -0.07
     cen
    -0.07
     Ragnar
    -0.07
    _dev
    -0.07
     Twig
    -0.07
    POSITIVE LOGITS
    �
    0.07
    amaha
    0.07
    בי
    0.07
    rzy
    0.07
    눙
    0.07
    evity
    0.06
    奥巴
    0.06
    eño
    0.06
    🏏
    0.06
    orgetown
    0.06
    Act Density 0.003%

    No Known Activations