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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🍾
    -0.08
    (pDX
    -0.07
    xDB
    -0.07
    瓖
    -0.07
    ㅜ
    -0.07
     PRE
    -0.07
    兕
    -0.07
    拽
    -0.07
    XL
    -0.07
    酏
    -0.07
    POSITIVE LOGITS
     помещения
    0.07
    גנים
    0.07
     kunnen
    0.07
    지는
    0.07
     get
    0.07
     Functions
    0.07
     waiter
    0.07
    سياسات
    0.07
     Seit
    0.07
    ']?>
    0.07
    Act Density 0.154%

    No Known Activations