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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exceptions or limitations

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

    Follows "not limited to"

    np_acts-logits-general · gemini-2.0-flash

    not limited to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    -0.77
    IUrlHelper
    -0.77
     estimés
    -0.77
    таратура
    -0.71
    ніципалі
    -0.66
    $_['
    -0.63
    WebElementEntity
    -0.60
     Baillargeon
    -0.60
    AndEndTag
    -0.60
    Дереккөздер
    -0.59
    POSITIVE LOGITS
     exhaustive
    0.81
     limited
    0.65
     exclusive
    0.64
    exhaus
    0.64
    exclusive
    0.60
     exklu
    0.60
     EXCLUSIVE
    0.60
     exhaus
    0.58
     Exclusive
    0.57
    Exclusive
    0.56
    Act Density 0.168%

    No Known Activations