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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    陆
    -0.08
    відом
    -0.06
    ISTRATION
    -0.06
    das
    -0.06
     기자
    -0.06
    _CHAN
    -0.06
    Win
    -0.06
    (ship
    -0.06
     pee
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    COPY
    0.07
     complying
    0.06
    .blue
    0.06
    ad
    0.06
    -lined
    0.06
    occupied
    0.06
    InView
    0.06
    .align
    0.06
     tiếp
    0.06
    Prime
    0.06
    Act Density 0.005%

    No Known Activations