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

    Neuronpedia

    INDEX
    Explanations

    0, -, _

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blogger
    -0.07
    
    -0.07
    intage
    -0.07
    ooky
    -0.07
     amateur
    -0.06
    杞
    -0.06
     getch
    -0.06
    /↵↵↵↵
    -0.06
    subplot
    -0.06
    summer
    -0.06
    POSITIVE LOGITS
     Para
    0.08
    𝚃
    0.08
    CAT
    0.08
     Tang
    0.08
    提交
    0.07
    内容
    0.07
    alu
    0.07
     Cape
    0.07
     Abu
    0.06
    ѭ
    0.06
    Act Density 0.002%

    No Known Activations