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

    Neuronpedia

    INDEX
    Explanations

    concepts related to questioning and answers

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

    Text preceding "answer" or "answers"

    np_acts-logits-general · gemini-2.0-flash

    providing answers to questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.75
    featureID
    -0.51
     Мексичка
    -0.48
    EDEFAULT
    -0.47
     InputDecoration
    -0.47
     tartalomajánló
    -0.46
    bitField
    -0.46
    *)((
    -0.46
    +#+
    -0.45
     nahilalakip
    -0.45
    POSITIVE LOGITS
     answer
    3.90
     answers
    3.54
    answer
    3.24
     answered
    3.20
     Answer
    3.16
    Answer
    2.97
     answering
    2.96
     ANSWER
    2.94
     Answers
    2.78
    answers
    2.66
    Act Density 0.656%

    No Known Activations