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

    Neuronpedia

    INDEX
    Explanations

    technical terms and jargon related to scientific and mathematical concepts

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

    linear guide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isNameExpr
    -0.57
    awaiter
    -0.56
    存于互联网档案馆
    -0.52
    ंदीखरीदारी
    -0.52
     arşivlendi
    -0.50
     nakalista
    -0.49
     OMITBAD
    -0.46
    KommentareTeilen
    -0.43
     CreateTagHelper
    -0.42
    DockStyle
    -0.42
    POSITIVE LOGITS
     informée
    0.85
    delwed
    0.56
    XmlType
    0.55
    ніципалі
    0.54
    soort
    0.52
    CloseOperation
    0.49
    peutic
    0.49
    InputTagHelper
    0.49
    tanleria
    0.48
    Jîn
    0.48
    Act Density 0.435%

    No Known Activations