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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contextual details about specific cases or examples

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

    in this case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.68
    IVEREF
    -0.64
    +#+#
    -0.56
     protoimpl
    -0.56
     pinulongan
    -0.55
    OGND
    -0.52
    styleType
    -0.52
     wireType
    -0.50
    pecabe
    -0.50
     kasarigan
    -0.50
    POSITIVE LOGITS
    的情况
    0.31
     Вікі
    0.30
    addAttribute
    0.30
    '>";
    0.29
    instancetype
    0.27
     situ
    0.27
    Życiorys
    0.27
     CASO
    0.27
    SetFont
    0.27
     Bisa
    0.26
    Act Density 0.045%

    No Known Activations