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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or logical operators typically used in programming

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

    logical conjunctions and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    drage
    -0.39
     ör
    -0.39
    webElementXpaths
    -0.39
     cono
    -0.37
    override
    -0.36
     pleaſure
    -0.36
     getSystem
    -0.35
    uste
    -0.35
     surat
    -0.35
    asteroide
    -0.35
    POSITIVE LOGITS
    Aholisi
    0.59
     שוליים
    0.48
     Pernambuco
    0.45
    Tembelea
    0.45
     مشين
    0.43
    脚注の使い方
    0.43
     autorytatywna
    0.42
    綜合報導
    0.42
    存于互联网档案馆
    0.41
     gynhyrchwyd
    0.41
    Act Density 0.307%

    No Known Activations