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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Authority
    -0.06
     Basic
    -0.06
    ара
    -0.06
    .Employee
    -0.06
     Sometimes
    -0.06
     معمول
    -0.06
     mnist
    -0.06
    Venue
    -0.06
     zich
    -0.06
     sizeof
    -0.06
    POSITIVE LOGITS
    圭
    0.06
    toolbar
    0.06
    intl
    0.06
     �
    0.06
    _Api
    0.06
    님
    0.06
    isplay
    0.06
    rooms
    0.06
    _FRAMEBUFFER
    0.06
     العالم
    0.06
    Act Density 0.002%

    No Known Activations