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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    全流程
    -0.08
    中国文化
    -0.08
     Blueprint
    -0.07
    ql
    -0.07
    setUp
    -0.07
    (dAtA
    -0.07
     ransom
    -0.07
     ועד
    -0.07
    回头看
    -0.07
    ılır
    -0.07
    POSITIVE LOGITS
    "]],↵
    0.07
    當
    0.07
    轨道
    0.07
    ном
    0.06
    য
    0.06
    ײ
    0.06
     muschi
    0.06
    朋
    0.06
    �
    0.06
    Discount
    0.06
    Act Density 0.303%

    No Known Activations