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

    Neuronpedia

    INDEX
    Explanations

    Attracting or tricking people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Assignable
    -0.07
    创新
    -0.07
     클
    -0.06
    اهش
    -0.06
     zusammen
    -0.06
    ควร
    -0.06
     getch
    -0.06
     Salem
    -0.06
     acab
    -0.06
    查
    -0.06
    POSITIVE LOGITS
     lure
    0.11
     Outer
    0.08
    条件
    0.07
     kafka
    0.07
     allure
    0.07
     Keywords
    0.07
    alary
    0.07
     Monster
    0.06
    	D
    0.06
     init
    0.06
    Act Density 0.007%

    No Known Activations