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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (dom
    -0.08
    .Android
    -0.07
    (WebDriver
    -0.07
    .AllowGet
    -0.07
    _grupo
    -0.07
    .students
    -0.07
    仍有
    -0.07
     gravid
    -0.07
    (hw
    -0.07
    舀
    -0.07
    POSITIVE LOGITS
    Arg
    0.07
    ating
    0.07
    ATION
    0.07
     remarkable
    0.07
     Semaphore
    0.07
    ated
    0.06
     Brothers
    0.06
    这家公司
    0.06
    าย
    0.06
    ал
    0.06
    Act Density 0.069%

    No Known Activations