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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their formatting in the text

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

    section numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnknownFieldSet
    -0.35
    InputTagHelper
    -0.35
     насељу
    -0.34
     först
    -0.34
     alimentación
    -0.33
    acjach
    -0.33
    Билгалдахарш
    -0.32
    ötzlich
    -0.32
     AMOUNT
    -0.31
     Sakit
    -0.31
    POSITIVE LOGITS
    subsubsection
    0.75
    subsection
    0.69
    wardship
    0.54
    `{.
    0.54
    PageIndex
    0.54
    subsec
    0.53
     '\\;'
    0.53
     متعلقه
    0.52
     constexpr
    0.52
    endish
    0.49
    Act Density 0.159%

    No Known Activations