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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating presence or inclusion of information

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

    containing or containing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.70
    ंदीखरीदारी
    -0.68
    parsedMessage
    -0.65
    windowFixed
    -0.62
     queſta
    -0.60
     Winaray
    -0.59
     TextAlign
    -0.57
     >=",
    -0.57
     utafitiHapana
    -0.56
     myſelf
    -0.56
    POSITIVE LOGITS
     contain
    0.92
     contains
    0.89
     contained
    0.82
     containing
    0.75
     Contains
    0.75
     contents
    0.75
    Contain
    0.74
     Contain
    0.74
     содержа
    0.73
    contain
    0.71
    Act Density 0.183%

    No Known Activations