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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or relatedness to groups or items

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

    a few of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -1.08
    IVEREF
    -0.86
    تقاوى
    -0.73
    GEBURTSDATUM
    -0.73
     оригіналу
    -0.70
     ſta
    -0.69
    Tembelea
    -0.68
    enderror
    -0.67
    AddTagHelper
    -0.67
     HFILL
    -0.67
    POSITIVE LOGITS
     Các
    0.33
     nossos
    0.31
     Nuestros
    0.31
    taciones
    0.31
     niitä
    0.31
     infatti
    0.30
     of
    0.30
     dintre
    0.29
     chúng
    0.29
    ônico
    0.29
    Act Density 0.013%

    No Known Activations