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

    Neuronpedia

    INDEX
    Explanations

    various forms of the article or determiner "la" across different contexts

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

    Non-English words or symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical and foreign language beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leçon
    -0.64
     paroisse
    -0.61
     faculté
    -0.61
     déput
    -0.61
    ônus
    -0.61
     negatives
    -0.60
     pandémie
    -0.60
     Myron
    -0.59
    lüssel
    -0.59
     charité
    -0.58
    POSITIVE LOGITS
    بوابة
    0.52
     fluorine
    0.47
    findpost
    0.46
    Biographie
    0.46
    RegressionTest
    0.45
     vinden
    0.45
    ėse
    0.44
     bromine
    0.44
    ándote
    0.43
    inė
    0.43
    Act Density 0.066%

    No Known Activations