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

    Neuronpedia

    INDEX
    Explanations

    references to films and entertainment-related terms

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

    Preceding words or phrases followed by "is"

    np_acts-logits-general · gemini-2.0-flash

    entity followed by is/was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -1.10
     فريبيس
    -1.09
    InputBorder
    -0.92
     تضيفلها
    -0.85
    rungsseite
    -0.83
     Chwiliwch
    -0.82
    RectangleBorder
    -0.81
     disambiguazione
    -0.81
    ISupport
    -0.81
    ArgsConstructor
    -0.81
    POSITIVE LOGITS
     is
    1.52
     merupakan
    1.33
     adalah
    1.26
     là
    0.99
    是一
    0.97
     represents
    0.94
     ialah
    0.93
    是一个
    0.92
    是一個
    0.91
     является
    0.90
    Act Density 0.571%

    No Known Activations