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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ent
    -0.07
     Fourth
    -0.06
    用户名
    -0.06
     ชนะ
    -0.06
     consulted
    -0.06
    53
    -0.06
    wendung
    -0.06
     Rise
    -0.06
     money
    -0.06
     phased
    -0.06
    POSITIVE LOGITS
    蜘蛛词
    0.07
    ніш
    0.07
     nimi
    0.07
     Eston
    0.07
     Scot
    0.06
     елек
    0.06
    iphy
    0.06
    licence
    0.06
    -ul
    0.06
     ÜNİVERSİTESİ
    0.06
    Act Density 0.022%

    No Known Activations