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

    Neuronpedia

    INDEX
    Explanations

    dance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Push
    -0.07
     gets
    -0.06
    Raw
    -0.06
     past
    -0.06
     raw
    -0.06
    Timeout
    -0.06
    (validate
    -0.06
     generates
    -0.06
    Get
    -0.06
     leftovers
    -0.06
    POSITIVE LOGITS
    迹
    0.07
     выпол
    0.07
     المن
    0.06
     الأرض
    0.06
     Cyber
    0.06
     lizard
    0.06
     عرب
    0.06
    hawks
    0.06
    /email
    0.06
     chees
    0.06
    Act Density 0.038%

    No Known Activations