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

    Neuronpedia

    INDEX
    Explanations

    instances of questions and answers in conversational text

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

    question and answer context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.49
    oredCriteria
    -0.46
    OGND
    -0.45
     ब्रेकडाउन
    -0.45
    protoimpl
    -0.44
    әрмәләр
    -0.43
    ArrowToggle
    -0.43
     disambiguazione
    -0.42
     modelAndView
    -0.41
     gmbh
    -0.40
    POSITIVE LOGITS
     answer
    0.85
    answer
    0.80
     Answer
    0.79
     answered
    0.78
    Answer
    0.76
     answering
    0.75
     answers
    0.74
     Q
    0.68
     Answers
    0.68
    answered
    0.68
    Act Density 0.071%

    No Known Activations