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

    Neuronpedia

    INDEX
    Explanations

    define/definition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ушы
    -0.08
    昌
    -0.07
    дыру
    -0.07
    .perform
    -0.07
    perform
    -0.07
     spots
    -0.07
    ланы
    -0.07
     opportunities
    -0.07
    -training
    -0.07
    菜
    -0.07
    POSITIVE LOGITS
     정의
    0.16
     definition
    0.14
    定义
    0.14
     Definition
    0.14
     definitions
    0.13
    _definition
    0.12
     Begriff
    0.12
    definition
    0.12
    Definition
    0.12
     تعریف
    0.12
    Act Density 0.063%

    No Known Activations