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

    Neuronpedia

    INDEX
    Explanations

    references to specific concepts and their significance in context

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

    help enable future actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.54
    AddTagHelper
    -0.50
     ſind
    -0.45
    ſchaft
    -0.44
    EndProject
    -0.43
     ſeine
    -0.43
     Audiodateien
    -0.42
    cookieParser
    -0.41
     miniaturka
    -0.41
     femininas
    -0.41
    POSITIVE LOGITS
     helped
    0.69
     helping
    0.68
     help
    0.67
     propel
    0.66
    帮助
    0.63
     helps
    0.62
     enable
    0.61
     prop
    0.61
     giúp
    0.59
     HELP
    0.57
    Act Density 0.144%

    No Known Activations