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

    Neuronpedia

    INDEX
    Explanations

    V

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的模样
    -0.08
     специально
    -0.07
    裣
    -0.07
    (Image
    -0.07
    跶
    -0.07
     месяцев
    -0.07
    晨报
    -0.07
    雒
    -0.06
     كافة
    -0.06
    expects
    -0.06
    POSITIVE LOGITS
     Giovanni
    0.07
     نظام
    0.07
     oppon
    0.07
    Ts
    0.06
    不舒服
    0.06
    it
    0.06
     CH
    0.06
    grim
    0.06
     Chavez
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations