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

    Neuronpedia

    INDEX
    Explanations

    the phrase "do this/so"

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.74
    GEBURTSDATUM
    -0.70
     defaultstate
    -0.65
    uxxxx
    -0.64
    ::~
    -0.62
     Paglinawan
    -0.62
    KURZBESCHREIBUNG
    -0.60
     QT
    -0.59
    quested
    -0.59
     décid
    -0.58
    POSITIVE LOGITS
     autorytatywna
    0.38
    <bos>
    0.38
    enumi
    0.38
     اسف
    0.38
    ghalaya
    0.37
    FormTagHelper
    0.36
    ものの
    0.35
    hof
    0.34
     GenerationType
    0.34
     LoggerFactory
    0.34
    Act Density 0.636%

    No Known Activations