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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly those related to quantities or identifiers

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

    Numbers followed by commas

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.85
     EconPapers
    -0.77
     autorytatywna
    -0.74
     InputDecoration
    -0.72
     الحره
    -0.69
    <unused60>
    -0.69
    <unused61>
    -0.68
    <unused63>
    -0.68
     NSCoder
    -0.68
    <unused62>
    -0.67
    POSITIVE LOGITS
     myſelf
    0.68
    ,–
    0.68
     itſelf
    0.65
    ,--
    0.62
    -,
    0.61
    ,-.
    0.61
     Monfieur
    0.59
     whoſe
    0.59
    ¹,
    0.58
     Theſe
    0.57
    Act Density 0.488%

    No Known Activations