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

    Neuronpedia

    INDEX
    Explanations

    won

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (place
    -0.08
     gauge
    -0.07
     proxy
    -0.07
    .dispatcher
    -0.07
     beginner
    -0.06
     haha
    -0.06
     」
    -0.06
    (INT
    -0.06
     pawn
    -0.06
     Ori
    -0.06
    POSITIVE LOGITS
    スコ
    0.07
     Aralık
    0.06
    بيع
    0.06
    られて
    0.06
     تست
    0.06
     nou
    0.06
     degrade
    0.06
    Eng
    0.06
    尖
    0.06
     conjunto
    0.06
    Act Density 0.023%

    No Known Activations