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

    Neuronpedia

    INDEX
    Explanations

    percentages

    oai_token-act-pair · gemini-2.0-flash

    percent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OwnProperty
    -0.55
     bombilla
    -0.51
    BeginInit
    -0.51
    oplayer
    -0.51
     ***!
    -0.50
     Normdatei
    -0.48
    __":
    -0.48
    cessed
    -0.48
     mẫu
    -0.48
    viewDidLoad
    -0.47
    POSITIVE LOGITS
     مشين
    0.60
     урна
    0.55
    Становништво
    0.50
    lgari
    0.48
     Commencez
    0.48
    <bos>
    0.48
    حياتها
    0.47
    OGND
    0.47
     الاطلاع
    0.46
    ervlak
    0.46
    Act Density 0.376%

    No Known Activations