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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data and temporal references in a text

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

    first, second, years, season

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.60
     Wikiseite
    -0.51
     NSCoder
    -0.45
    endpush
    -0.45
     Affiliations
    -0.44
    iços
    -0.44
     
    -0.44
    KURZBESCHREIBUNG
    -0.43
     Subtitle
    -0.43
     SSE
    -0.43
    POSITIVE LOGITS
     helft
    0.40
    特に
    0.40
     initially
    0.37
     Hälfte
    0.36
     voran
    0.35
     Initially
    0.34
     first
    0.34
     Marte
    0.34
    tadır
    0.34
     primero
    0.34
    Act Density 0.179%

    No Known Activations