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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    物质
    -0.07
    Э
    -0.07
    ritis
    -0.07
    钾
    -0.07
    体
    -0.06
    positories
    -0.06
    ebx
    -0.06
    Б
    -0.06
    =index
    -0.06
     mammals
    -0.06
    POSITIVE LOGITS
    最优
    0.07
    Slide
    0.07
     unfortunate
    0.07
    闲置
    0.07
    <Comment
    0.07
    _whitespace
    0.07
    下调
    0.07
    越发
    0.07
    越来越多
    0.07
     promotional
    0.07
    Act Density 0.020%

    No Known Activations