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

    Neuronpedia

    INDEX
    Explanations

    data related to numerical statistics or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Phone numbers or numbers with dashes

    np_acts-logits-general · gemini-2.0-flash

    phone numbers and contacts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     typelib
    -0.94
    :✨
    -0.82
     ProtoMessage
    -0.80
    Personensuche
    -0.73
     <<<<<<<<<<<<<<
    -0.69
     تضيفلها
    -0.68
    XmlEnum
    -0.67
    Personendaten
    -0.65
     externi
    -0.64
    Diweddarwch
    -0.64
    POSITIVE LOGITS
    versy
    0.67
    ToBounds
    0.64
    berton
    0.61
    ază
    0.57
     Déf
    0.56
     baths
    0.54
    conio
    0.53
    Grüsse
    0.53
    psons
    0.53
    ädie
    0.52
    Act Density 0.209%

    No Known Activations