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

    Neuronpedia

    INDEX
    Explanations

    phrases that express surprise or unexpectedness

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

    expressing surprise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.53
    الإنجليزية
    -0.47
    جغرافيا
    -0.44
     Comprometido
    -0.43
     computadoras
    -0.42
     fotográfico
    -0.40
     manicura
    -0.40
    thyst
    -0.40
     rambut
    -0.39
     extremos
    -0.39
    POSITIVE LOGITS
    难怪
    0.67
     why
    0.60
    recognized
    0.54
    evident
    0.54
     evident
    0.52
    comparable
    0.50
     Huff
    0.49
     recognized
    0.49
    proven
    0.48
    attractive
    0.48
    Act Density 0.009%

    No Known Activations