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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that are digits or parts of date/time strings (numbers, years, and date fragments).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     Grat
    -0.10
     arsenal
    -0.09
     cane
    -0.09
     Zar
    -0.09
     Bea
    -0.09
     McGr
    -0.09
     Lor
    -0.09
     compl
    -0.09
     Beau
    -0.09
     FIG
    -0.08
    POSITIVE LOGITS
    ÂĢÂĢ
    0.10
    .Dictionary
    0.10
    âĸłâĸł
    0.10
    LLU
    0.09
    entes
    0.09
     CUT
    0.09
     cut
    0.09
    cü
    0.08
     baģlantılar
    0.08
    Äı
    0.08
    Act Density 0.000%

    No Known Activations