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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases indicating relationships or conditions

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

    foreign prepositions and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !
    -0.34
    KindOfClass
    -0.32
     Trä
    -0.30
    ol
    -0.30
    .
    -0.30
     مشين
    -0.29
     {},
    -0.28
     Kruse
    -0.28
     témoignage
    -0.28
     Kriminal
    -0.28
    POSITIVE LOGITS
     nahilalakip
    0.79
     esternos
    0.72
     AssemblyTitle
    0.71
    SequentialGroup
    0.70
    ディネート
    0.68
    ؼ
    0.66
     EconPapers
    0.66
    majánló
    0.66
     للاسماء
    0.64
    səhifə
    0.62
    Act Density 0.012%

    No Known Activations