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

    Neuronpedia

    INDEX
    Explanations

    pay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     veins
    -0.07
    悠
    -0.07
    .databinding
    -0.06
    IEEE
    -0.06
    Defense
    -0.06
     Majesty
    -0.06
     Aquarium
    -0.06
    .Tele
    -0.06
     ＜
    -0.06
    ến
    -0.06
    POSITIVE LOGITS
    พย
    0.07
     organizace
    0.06
     FLASH
    0.06
     Sox
    0.06
    approval
    0.06
     Class
    0.06
     заказ
    0.06
     bi
    0.06
    뮤
    0.06
     borderline
    0.06
    Act Density 0.015%

    No Known Activations