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

    Neuronpedia

    INDEX
    Explanations

    code snippets where a buffer is being converted to base64

    oai_token-act-pair · gemini-2.0-flash

    Data encoding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kháu
    -0.68
     keys
    -0.68
    interopRequire
    -0.61
    uxxxx
    -0.60
     khóa
    -0.60
    apunov
    -0.58
    UnusedPrivate
    -0.57
    XmlAccessType
    -0.57
     encryption
    -0.57
     AssemblyCompany
    -0.57
    POSITIVE LOGITS
    base
    0.61
     base
    0.60
    Base
    0.58
     Base
    0.56
    ScopeManager
    0.54
    τρο
    0.50
    XmlAccessorType
    0.49
    おき
    0.48
    BASE
    0.47
    tah
    0.46
    Act Density 1.117%

    No Known Activations