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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and their relationships in a given context

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

    years, numbers, dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.75
     ब्रेकडाउन
    -0.61
    IsContent
    -0.59
     Савезне
    -0.59
    Personensuche
    -0.57
    AddTagHelper
    -0.53
    حوالہ
    -0.52
     HasFactory
    -0.51
     Administrativna
    -0.50
     Мексичка
    -0.50
    POSITIVE LOGITS
    ToAction
    0.54
     detailed
    0.53
    detailed
    0.48
     ویکی‌پدیای
    0.48
     Detailed
    0.47
    Detailed
    0.45
    NewReader
    0.43
     Important
    0.42
    今
    0.42
     FAQs
    0.42
    Act Density 0.031%

    No Known Activations