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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    slideUp
    -0.07
     film
    -0.06
    ̈
    -0.06
    ’ı
    -0.06
     Wii
    -0.06
     fucking
    -0.06
    เมตร
    -0.06
    .attack
    -0.06
     luc
    -0.06
    uen
    -0.06
    POSITIVE LOGITS
    有限公司
    0.07
     agendas
    0.07
     Northwest
    0.06
     достиг
    0.06
    +(
    0.06
    -forward
    0.06
     الأسر
    0.06
     McG
    0.06
     مج
    0.06
    在线视频
    0.06
    Act Density 0.007%

    No Known Activations