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

    Neuronpedia

    INDEX
    Explanations

    process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _os
    -0.07
     зустрі
    -0.07
    -Regular
    -0.07
     desperately
    -0.06
     vulner
    -0.06
    atório
    -0.06
    )],↵
    -0.06
     운영자
    -0.06
     розви
    -0.06
    ulators
    -0.06
    POSITIVE LOGITS
     Zam
    0.07
    Names
    0.07
    لاث
    0.07
    temps
    0.06
     $("
    0.06
     pem
    0.06
     kadın
    0.06
     청
    0.06
     Pike
    0.06
     SEG
    0.06
    Act Density 0.002%

    No Known Activations