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

    Neuronpedia

    INDEX
    Explanations

    sentences that express states of being, particularly regarding one's identity or condition

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

    French and related Romance language

    np_acts-logits-general · gemini-2.0-flash

    je suis / it is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Theſe
    -0.65
     pauv
    -0.63
     oras
    -0.60
     nahilalakip
    -0.57
     Diſ
    -0.57
     autorité
    -0.56
     wikipagina
    -0.56
    HomeAsUpEnabled
    -0.55
     flesta
    -0.54
     stället
    -0.54
    POSITIVE LOGITS
    Portale
    0.54
     very
    0.53
     est
    0.52
    verwijspagina
    0.52
    ICIOS
    0.50
     helt
    0.50
     tan
    0.49
     }}=\
    0.49
    XMLSchema
    0.48
    تقاوى
    0.48
    Act Density 0.146%

    No Known Activations