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

    Neuronpedia

    INDEX
    Explanations

    HTML language attributes in documents

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

    language specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.70
    batore
    -0.67
    writeFieldEnd
    -0.66
    ագրություններ
    -0.66
     TestBed
    -0.60
     bede
    -0.59
     חיצוניים
    -0.59
    ollection
    -0.59
     Савезне
    -0.59
     Paglinawan
    -0.58
    POSITIVE LOGITS
     lang
    0.74
     linguagem
    0.70
     language
    0.66
     Sprache
    0.63
    lang
    0.63
     Language
    0.60
     Lang
    0.59
     LANG
    0.58
    language
    0.57
     lenguaje
    0.55
    Act Density 0.002%

    No Known Activations