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

    Neuronpedia

    INDEX
    Explanations

    the start of new content or sections within the text

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

    Follows a capitalized word or abbreviation

    np_acts-logits-general · gemini-2.0-flash

    Introduce features or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.75
     CreateTagHelper
    -0.60
    _->
    -0.57
     tartalomajánló
    -0.54
     createState
    -0.53
    ->$
    -0.53
    IsContent
    -0.52
     AttributeSet
    -0.52
    رها
    -0.50
     Paglinawan
    -0.49
    POSITIVE LOGITS
    Featuring
    0.92
     Featuring
    0.84
    Offering
    0.77
     feature
    0.77
     features
    0.75
     Guests
    0.73
     guests
    0.71
     Offering
    0.70
    features
    0.68
    Providing
    0.67
    Act Density 0.044%

    No Known Activations