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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    路面
    -0.07
    .address
    -0.07
     Ben
    -0.07
    漳州
    -0.07
    逅
    -0.07
    Ճ
    -0.07
     зрения
    -0.07
    _CN
    -0.06
    备考
    -0.06
     your
    -0.06
    POSITIVE LOGITS
    点缀
    0.07
    巨头
    0.07
     comentário
    0.06
     fetal
    0.06
    facts
    0.06
    晡
    0.06
     permissions
    0.06
    (Model
    0.06
     --------------------------------
    0.06
     обрат
    0.06
    Act Density 0.001%

    No Known Activations