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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the act of providing information or resources

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

    providing information, explanations, or evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PDOException
    -0.54
     omnia
    -0.45
    RenderAtEndOf
    -0.44
    transQ
    -0.44
    olymp
    -0.43
     ſch
    -0.41
     htons
    -0.41
    :///
    -0.41
     totalPrice
    -0.41
    よろしくお願いします
    -0.40
    POSITIVE LOGITS
     lenker
    0.68
     제공
    0.62
     provided
    0.61
     Provide
    0.58
     provide
    0.57
     explanations
    0.57
     guidance
    0.56
    Provide
    0.54
     insights
    0.52
     gave
    0.52
    Act Density 0.073%

    No Known Activations