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

    Neuronpedia

    INDEX
    Explanations

    pps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivative
    -0.07
    粮
    -0.07
     зарегистрирова
    -0.07
     son
    -0.07
    =z
    -0.07
    管理和
    -0.06
    赛车
    -0.06
    闪光
    -0.06
    nm
    -0.06
     Eigen
    -0.06
    POSITIVE LOGITS
    aceut
    0.07
     kart
    0.07
    .They
    0.07
     rebuild
    0.07
     attending
    0.07
    �
    0.07
    手艺
    0.07
     Prot
    0.07
     obstruct
    0.07
    columns
    0.06
    Act Density 0.001%

    No Known Activations