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

    Neuronpedia

    INDEX
    Explanations

    temporal expressions referencing weeks and years

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

    time periods

    np_acts-logits-general · gemini-2.0-flash

    time units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     today
    -0.97
     yesterday
    -0.90
     ostavi
    -0.87
     aujourd
    -0.87
     wireType
    -0.86
     hoy
    -0.85
     hoje
    -0.83
     сегодня
    -0.83
     propOrder
    -0.82
    today
    -0.82
    POSITIVE LOGITS
     scolas
    0.55
     hinweg
    0.48
    amssymb
    0.47
     disparu
    0.45
     atrás
    0.44
     میل
    0.43
    ToBounds
    0.43
     because
    0.42
    varande
    0.41
     során
    0.41
    Act Density 0.320%

    No Known Activations