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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     Eat
    -0.07
     perfection
    -0.07
    奏
    -0.07
    Serializer
    -0.07
     telescope
    -0.07
    人员
    -0.07
    更新
    -0.07
    内存
    -0.07
    PLE
    -0.06
    POSITIVE LOGITS
    뭏
    0.08
    最も
    0.08
    Relations
    0.07
    גובות
    0.07
    ན
    0.07
    _brand
    0.07
     MULTI
    0.07
     Marxism
    0.07
     Third
    0.07
    ıkl
    0.07
    Act Density 0.029%

    No Known Activations