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

    Neuronpedia

    INDEX
    Explanations

    questions and interrogative phrases

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

    questions ending with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects questions—tokens and contexts that form interrogative sentences (question words and/or a question mark).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.46
     referrerpolicy
    -0.45
    <>
    -0.42
    GEBURTSDATUM
    -0.41
    ]$}
    -0.40
     withal
    -0.40
    jspb
    -0.40
    mybatisplus
    -0.38
     emailAlready
    -0.38
    routeProvider
    -0.38
    POSITIVE LOGITS
     للمعارف
    0.51
     resourceCulture
    0.46
     للاسماء
    0.45
    المناصب
    0.43
    DockStyle
    0.42
     propOrder
    0.42
    ثيق
    0.40
    AccessorTable
    0.40
     boneco
    0.39
    MessageTagHelper
    0.38
    Act Density 0.042%

    No Known Activations