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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     サ
    -0.07
    限
    -0.06
     따
    -0.06
    faq
    -0.06
     sober
    -0.06
     cheg
    -0.06
     pioneered
    -0.06
    Insensitive
    -0.06
    _upper
    -0.06
     Sist
    -0.06
    POSITIVE LOGITS
    runs
    0.07
    不过
    0.06
     perpetr
    0.06
     Consumers
    0.06
     اندازه
    0.06
    Including
    0.06
     наприклад
    0.06
     dissolve
    0.06
    idal
    0.06
    (now
    0.06
    Act Density 0.003%

    No Known Activations