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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Orders
    -0.07
    .restaurant
    -0.07
    .Is
    -0.07
    .month
    -0.07
    RACT
    -0.07
     rinse
    -0.07
    ак
    -0.07
    整整
    -0.06
    工程技术
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ling
    0.07
     Dove
    0.07
    한다
    0.06
    脾胃
    0.06
    Cookies
    0.06
     ubuntu
    0.06
     kitty
    0.06
    笔
    0.06
    ＄
    0.06
    גישה
    0.06
    Act Density 0.023%

    No Known Activations