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

    Neuronpedia

    INDEX
    Explanations

    phrases involving an expression of knowledge or certainty

    oai_token-act-pair · gemini-2.0-flash

    knowledge/telling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.66
     Вікі
    -0.58
     continúas
    -0.58
     nakalista
    -0.58
    TagHelper
    -0.58
    ContentAsync
    -0.56
    είου
    -0.56
    bkz
    -0.56
    mstyle
    -0.54
    Pyx
    -0.51
    POSITIVE LOGITS
     NSCoder
    0.77
    BeforeMethod
    0.56
    /******/
    0.54
    UpInside
    0.53
    hoppers
    0.51
    PreExecute
    0.49
    getOutputStream
    0.49
     Ezra
    0.49
    Plural
    0.49
     parseFrom
    0.48
    Act Density 0.428%

    No Known Activations