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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships involving entities and their attributes in various contexts

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

    quantifiers or generics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zwiſchen
    -0.91
    ſicht
    -0.89
    :✨
    -0.87
     dieſes
    -0.87
     zuſammen
    -0.85
    ſſung
    -0.85
    httphttps
    -0.84
     deſſen
    -0.84
    iſche
    -0.83
     Menſchen
    -0.82
    POSITIVE LOGITS
     any
    0.52
    这类
    0.50
     many
    0.49
     çoğu
    0.49
     wielu
    0.47
     takich
    0.47
     jeweiligen
    0.45
     qualquer
    0.43
     qualsiasi
    0.43
     любом
    0.43
    Act Density 0.344%

    No Known Activations