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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Properties
    -0.07
     четвер
    -0.07
     arises
    -0.07
    145
    -0.06
    粒
    -0.06
     숨
    -0.06
    Improved
    -0.06
     ultimately
    -0.06
    ーロ
    -0.06
     efect
    -0.06
    POSITIVE LOGITS
    úde
    0.07
    ripsi
    0.07
     Garmin
    0.06
    car
    0.06
    krv
    0.06
    }_${
    0.06
    bild
    0.06
     Çev
    0.06
    ừng
    0.06
    .setDescription
    0.06
    Act Density 0.175%

    No Known Activations