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

    Neuronpedia

    INDEX
    Explanations

    numeric values and data related to publications

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

    Numbers followed by a closing parenthesis

    np_acts-logits-general · gemini-2.0-flash

    citation numbers in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     %@",
    -0.53
     Once
    -0.49
    ///**
    -0.48
     ▲
    -0.48
    Grado
    -0.48
     once
    -0.48
    %@",
    -0.48
    addCriterion
    -0.48
    nste
    -0.48
    */
    -0.47
    POSITIVE LOGITS
     yılı
    0.60
    HideFlags
    0.59
     Савезне
    0.57
    adaptiveStyles
    0.56
     الرياضيه
    0.56
    RectangleBorder
    0.54
     BoxDecoration
    0.54
     traduzione
    0.53
    Хьажоргаш
    0.53
    pirazione
    0.53
    Act Density 0.217%

    No Known Activations