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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating degrees of emphasis or intensity

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

    so X that Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.71
    AddTagHelper
    -0.68
    TypedDataSet
    -0.60
    queryInterface
    -0.59
    MessageOf
    -0.57
    TagMode
    -0.56
    LikeLike
    -0.54
    IntoConstraints
    -0.54
     Wicidata
    -0.53
    XmlAccessorType
    -0.52
    POSITIVE LOGITS
     sogar
    0.51
     zelfs
    0.49
     even
    0.47
     persino
    0.44
     nawet
    0.44
     addirittura
    0.43
     incluso
    0.40
     даже
    0.40
    甚至
    0.40
     dokonce
    0.39
    Act Density 0.018%

    No Known Activations