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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ظهر
    -0.07
    004
    -0.07
    Regarding
    -0.07
    侯
    -0.07
    傷
    -0.06
    Monad
    -0.06
    保障
    -0.06
     celebrate
    -0.06
    #ifdef
    -0.06
    ér
    -0.06
    POSITIVE LOGITS
     Quartz
    0.07
     Algorithms
    0.06
    img
    0.06
     yaşan
    0.06
     домашних
    0.06
    BL
    0.06
    чески
    0.06
    帖
    0.06
     */)
    0.06
    INF
    0.06
    Act Density 0.022%

    No Known Activations