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

    Neuronpedia

    INDEX
    Explanations

    titles or names of individuals and their descriptors

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

    "[Word] is" or "[Word] was" sentences

    np_acts-logits-general · gemini-2.0-flash

    is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.82
    XmlAccessType
    -0.81
     ModelExpression
    -0.80
    ISupport
    -0.78
     تضيفلها
    -0.76
    InputBorder
    -0.76
    PreferredItem
    -0.73
     StringTokenizer
    -0.72
    )++;
    -0.68
     typelib
    -0.67
    POSITIVE LOGITS
     is
    1.63
     adalah
    1.47
     merupakan
    1.35
     là
    1.24
     ialah
    1.16
     является
    1.08
    是一
    1.07
     είναι
    1.03
    是
    1.01
    是一种
    0.99
    Act Density 0.853%

    No Known Activations