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

    Neuronpedia

    INDEX
    Explanations

    TODO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Attributes
    -0.06
    инок
    -0.06
    iy
    -0.06
     narration
    -0.06
     converse
    -0.06
     Xin
    -0.06
    (Socket
    -0.06
    _put
    -0.06
     từ
    -0.06
     ApplicationContext
    -0.06
    POSITIVE LOGITS
    Activ
    0.07
     poco
    0.06
    aji
    0.06
     nuevas
    0.06
     prise
    0.06
     Ged
    0.06
    OLUM
    0.06
    ियम
    0.06
     адрес
    0.06
     Vie
    0.06
    Act Density 0.002%

    No Known Activations