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

    Neuronpedia

    INDEX
    Explanations

    is/are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    直流
    -0.08
     uint
    -0.07
     ByteArrayInputStream
    -0.07
    .RESET
    -0.07
    答疑
    -0.07
     infile
    -0.07
    toDate
    -0.07
    滢
    -0.07
    elsius
    -0.07
     wreak
    -0.07
    POSITIVE LOGITS
     polit
    0.07
    chap
    0.07
    COMM
    0.07
    icz
    0.06
    斯塔
    0.06
    珲
    0.06
    lac
    0.06
    gua
    0.06
    ייב
    0.06
    컨
    0.06
    Act Density 0.122%

    No Known Activations