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

    Neuronpedia

    INDEX
    Explanations

    license and stark contrast

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ali
    -0.08
    ено
    -0.07
    جميع
    -0.07
    zenia
    -0.07
    (blob
    -0.07
    Loaded
    -0.07
    presso
    -0.07
    żenia
    -0.07
     المص
    -0.07
    ternal
    -0.06
    POSITIVE LOGITS
     cap
    0.08
     сни
    0.07
     pozosta
    0.07
     opi
    0.07
    鲏
    0.07
     Accessed
    0.07
    мотр
    0.06
    出台
    0.06
     rests
    0.06
    扫黑
    0.06
    Act Density 0.001%

    No Known Activations