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

    Neuronpedia

    INDEX
    Explanations

    words related to phone numbers and mobile devices in a language other than English

    oai_token-act-pair · gemini-2.0-flash

    diverse language tokens

    np_token-act-pair-logits · gpt-4o-mini

    non-english text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.64
    TagHelper
    -0.57
    KURZBESCHREIBUNG
    -0.53
    IsContent
    -0.49
    gestone
    -0.47
    HtmlAttribute
    -0.45
    setVerticalGroup
    -0.44
    SourceChecksum
    -0.44
    letzt
    -0.44
     BoxFit
    -0.44
    POSITIVE LOGITS
     lenker
    0.69
     Walkover
    0.56
    ربية
    0.52
    jenost
    0.52
    Ashlee
    0.52
    っこう
    0.49
    iseries
    0.49
    enment
    0.48
     Banks
    0.48
    Искәрмәләр
    0.47
    Act Density 0.566%

    No Known Activations