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

    Neuronpedia

    INDEX
    Explanations

    references to singular articles in various languages

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

    articles before nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     honneur
    -0.67
     infância
    -0.63
     enfance
    -0.60
     identité
    -0.59
    /*
    -0.58
     autorité
    -0.56
    hláš
    -0.56
     acepción
    -0.55
     orilla
    -0.55
    Erreferentziak
    -0.54
    POSITIVE LOGITS
     a
    1.16
     una
    1.05
     an
    1.01
     einen
    0.85
     একটি
    0.81
     einem
    0.81
     ஒரு
    0.78
    一个
    0.77
     một
    0.77
     einer
    0.77
    Act Density 0.005%

    No Known Activations