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

    Neuronpedia

    INDEX
    Explanations

    examples of quantifiers and their usage in language

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

    phrase-final morphemes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.64
    PYX
    -0.59
    IsInitialized
    -0.57
    copg
    -0.57
    期刊论文
    -0.56
    تقاوى
    -0.55
     Italijanski
    -0.55
    VersionUID
    -0.55
     дописавши
    -0.55
    ktop
    -0.55
    POSITIVE LOGITS
     behavioral
    0.26
    Портали
    0.26
    物
    0.26
    ifikationer
    0.26
     văn
    0.26
     violeta
    0.26
    блон
    0.25
     КП
    0.25
     elä
    0.24
    ✌️
    0.24
    Act Density 0.058%

    No Known Activations