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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    起点
    -0.08
    ọc
    -0.08
    wards
    -0.08
    .solution
    -0.07
    きっかけ
    -0.07
    sj
    -0.07
     Carn
    -0.07
    育儿
    -0.07
    -chief
    -0.07
    /topics
    -0.07
    POSITIVE LOGITS
     Vader
    0.08
     beep
    0.07
     restrained
    0.07
    _HTML
    0.07
     pute
    0.06
     Debug
    0.06
     OLED
    0.06
     narrow
    0.06
     nave
    0.06
    ᴸ
    0.06
    Act Density 0.011%

    No Known Activations