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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ftar
    -0.08
    硭
    -0.07
    (us
    -0.07
    炆
    -0.07
    蛃
    -0.07
     Besides
    -0.07
    锾
    -0.07
     terug
    -0.07
    葸
    -0.07
     weak
    -0.07
    POSITIVE LOGITS
    TÜ
    0.07
     iv
    0.07
     여
    0.07
    aye
    0.07
     NVIDIA
    0.07
     thêm
    0.07
     tagged
    0.07
    �
    0.07
    უ
    0.07
    Painter
    0.07
    Act Density 0.089%

    No Known Activations