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

    Neuronpedia

    INDEX
    Explanations

    arrow functions commonly used in Javascript (=>)

    oai_token-act-pair · gemini-2.0-flash

    =>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.95
     =>
    -1.00
    =>
    -0.80
     =>
    -0.77
     StatelessWidget
    -0.59
    ’
    -0.58
     =>{
    -0.52
    =>{
    -0.52
    '
    -0.51
    ==>
    -0.50
    POSITIVE LOGITS
    featureID
    0.76
    Personendaten
    0.76
     متعلقه
    0.74
    Obrázky
    0.66
    parsedMessage
    0.65
    :✨
    0.65
    RetentionPolicy
    0.64
    InputTagHelper
    0.61
     ویکی‌پدیا
    0.60
    DoubleQuotes
    0.60
    Act Density 0.546%

    No Known Activations