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

    Neuronpedia

    INDEX
    Explanations

    numerical data points and values that are related to scientific references

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

    years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.79
     AttributeSet
    -0.64
    fjspx
    -0.63
    Rüyada
    -0.61
    المناصب
    -0.61
    abestanden
    -0.60
     فريبيس
    -0.59
     nahilalakip
    -0.58
     ویکی‌پدیا
    -0.57
    richTextPanel
    -0.57
    POSITIVE LOGITS
    참고
    0.50
     Correa
    0.41
     colour
    0.41
    SHOT
    0.38
     voc
    0.37
     bought
    0.37
     kla
    0.37
     Sz
    0.37
     centre
    0.36
    FF
    0.36
    Act Density 0.125%

    No Known Activations