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

    Neuronpedia

    INDEX
    Explanations

    various types of quotation marks and string delimiters

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

    group names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.66
     propOrder
    -0.65
    IsMutable
    -0.65
     تضيفلها
    -0.64
     Chwiliwch
    -0.63
     defaultstate
    -0.60
     وتسجيلات
    -0.60
     lenker
    -0.59
     дописавши
    -0.59
    ConstraintMaker
    -0.59
    POSITIVE LOGITS
    ・)
    0.45
     "}
    0.41
     Charle
    0.39
    Biographical
    0.39
    "
    0.38
    Bent
    0.38
    asteel
    0.37
    localPosition
    0.37
    onesome
    0.37
    enus
    0.37
    Act Density 0.015%

    No Known Activations