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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embodies
    -0.07
     evenings
    -0.07
    ур
    -0.06
     بگیر
    -0.06
     presents
    -0.06
     performer
    -0.06
     Erick
    -0.06
     Guard
    -0.06
     три
    -0.06
    两个
    -0.06
    POSITIVE LOGITS
    读
    0.07
    جوی
    0.07
     Rus
    0.06
    Unt
    0.06
    cház
    0.06
    _home
    0.06
    обы
    0.06
     babel
    0.06
     rin
    0.06
     Hollande
    0.06
    Act Density 0.000%

    No Known Activations