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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     度
    -0.07
    strument
    -0.07
    れど
    -0.06
    闻
    -0.06
     Prevention
    -0.06
     ～
    -0.06
    Registered
    -0.06
    有关
    -0.06
    .XtraPrinting
    -0.06
    ocus
    -0.06
    POSITIVE LOGITS
     aplik
    0.07
    initialize
    0.07
    :UIControlEventTouchUpInside
    0.07
    expected
    0.07
     Hong
    0.07
     creditor
    0.06
    (edge
    0.06
     проводить
    0.06
     talent
    0.06
    $,
    0.06
    Act Density 0.066%

    No Known Activations