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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    吊顶
    -0.07
     reflux
    -0.07
     Turkish
    -0.07
     Jesús
    -0.07
     Meh
    -0.07
     Loft
    -0.06
    平均每
    -0.06
     Belgium
    -0.06
    /login
    -0.06
     кафе
    -0.06
    POSITIVE LOGITS
    逮捕
    0.07
    =>"
    0.07
    ürü
    0.06
    ሙ
    0.06
    路过
    0.06
    sız
    0.06
    .cn
    0.06
    rawn
    0.06
    andra
    0.06
    ʹ
    0.06
    Act Density 0.030%

    No Known Activations