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

    Neuronpedia

    INDEX
    Explanations

    structured data and coding patterns related to data aggregation and processing

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

    user-defined functions and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -1.08
     betweenstory
    -0.98
     Мексичка
    -0.98
    Rujuakan
    -0.88
    IUrlHelper
    -0.86
     autorytatywna
    -0.85
    VYMaps
    -0.85
    ItemBackground
    -0.85
    LookAnd
    -0.84
     <<<<<<<<<<<<<<
    -0.80
    POSITIVE LOGITS
     likewise
    0.45
     ditto
    0.44
     ebenfalls
    0.41
    同じく
    0.41
     ayrıca
    0.40
     كذلك
    0.37
     also
    0.37
     equally
    0.36
     Likewise
    0.36
     similarly
    0.34
    Act Density 2.521%

    No Known Activations