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

    Neuronpedia

    INDEX
    Explanations

    formal email salutations

    oai_token-act-pair · gemini-2.0-flash

    Dear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.94
    RegistryLite
    -0.89
     Normdatei
    -0.86
    LayoutStyle
    -0.85
     AssemblyCulture
    -0.80
    addCriterion
    -0.80
    QMetaType
    -0.79
     وتسجيلات
    -0.79
     Archiproducts
    -0.79
    ModelAdmin
    -0.79
    POSITIVE LOGITS
    Dear
    0.69
    Hi
    0.63
    hi
    0.55
    if
    0.51
     Dear
    0.50
    Hello
    0.50
     Hi
    0.49
    <b>
    0.47
     chers
    0.47
    The
    0.46
    Act Density 0.884%

    No Known Activations