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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to health metrics or measurements

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

    the number 0

    np_acts-logits-general · gemini-2.0-flash

    multilingual technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    -0.62
    ↵↵
    -0.55
     "
    -0.53
     
    -0.52
     si
    -0.50
      
    -0.50
    候
    -0.50
     [
    -0.50
     «
    -0.49
     v
    -0.48
    POSITIVE LOGITS
    脚注の使い方
    1.31
    ConstraintMaker
    1.28
    ंदीखरीदारी
    1.26
     مشين
    1.24
     utafitiHapana
    1.20
     المعيارى
    1.19
    InjectAttribute
    1.18
    AndEndTag
    1.18
     فريبيس
    1.18
     Efq
    1.17
    Act Density 0.641%

    No Known Activations