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

    Neuronpedia

    INDEX
    Explanations

    underline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dispute
    -0.07
    大面积
    -0.07
    볕
    -0.07
    _MUT
    -0.07
    觖
    -0.06
    辅导
    -0.06
    砾
    -0.06
     древ
    -0.06
    �
    -0.06
    祖
    -0.06
    POSITIVE LOGITS
    ادات
    0.07
    一期
    0.07
     lowest
    0.07
    家乡
    0.07
     tabela
    0.07
    Banner
    0.07
     ORM
    0.07
    lining
    0.07
    <tool_call>
    0.06
    Urls
    0.06
    Act Density 0.001%

    No Known Activations