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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

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

    past states or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MultipartFile
    -0.45
    تقاوى
    -0.44
    nestjs
    -0.43
    عرِّف
    -0.41
     ä
    -0.39
    Portail
    -0.38
    astéro
    -0.38
    Kanpo
    -0.37
    itatem
    -0.35
    wget
    -0.35
    POSITIVE LOGITS
     nakalista
    0.60
     previously
    0.60
     bekas
    0.56
    expandindo
    0.55
     originally
    0.55
     tidigare
    0.54
    ruik
    0.54
     previous
    0.53
    previously
    0.53
     vorher
    0.52
    Act Density 0.035%

    No Known Activations