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

    Neuronpedia

    INDEX
    Explanations

    questions indicated by the word "question" and its variations

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

    "question"

    np_acts-logits-general · gemini-2.0-flash

    poses a question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]-'
    -0.96
    ]='\
    -0.81
    Personendaten
    -0.80
    WriteTagHelper
    -0.75
    Empereur
    -0.74
    empereur
    -0.73
    (;;)
    -0.72
     edn
    -0.72
    Tembelea
    -0.72
    Cyfeiriadau
    -0.71
    POSITIVE LOGITS
     questions
    1.33
     Question
    1.19
     Questions
    1.17
    Questions
    1.12
     question
    1.11
    questions
    1.10
     QUESTION
    1.00
    question
    0.99
    Ques
    0.96
    Question
    0.95
    Act Density 0.054%

    No Known Activations