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

    Neuronpedia

    INDEX
    Explanations

    Satellites and orbits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     데이터
    -0.08
     تعلم
    -0.08
     santé
    -0.08
    leyen
    -0.07
     확인
    -0.07
     صحة
    -0.07
    .Preference
    -0.07
     회원
    -0.07
     aligns
    -0.07
    ной
    -0.07
    POSITIVE LOGITS
     bells
    0.09
     craz
    0.09
     magnific
    0.08
     dildo
    0.08
    arie
    0.08
    bers
    0.08
     glam
    0.08
     daughters
    0.08
     magní
    0.08
     perched
    0.08
    Act Density 0.002%

    No Known Activations