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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks/parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     化
    -0.07
    .student
    -0.07
    min
    -0.07
    /mark
    -0.07
     данные
    -0.07
     lương
    -0.06
     n
    -0.06
    MIN
    -0.06
     khuyến
    -0.06
    4
    -0.06
    POSITIVE LOGITS
    。“
    0.08
     subject
    0.07
    brıs
    0.07
    のも
    0.06
    EH
    0.06
    >'
    0.06
    orra
    0.06
    Act
    0.06
    EI
    0.06
     daleko
    0.06
    Act Density 0.040%

    No Known Activations