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

    Neuronpedia

    INDEX
    Explanations

    references to time, specifically regarding past and future events

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

    "Later" or "earlier" in time

    np_acts-logits-general · gemini-2.0-flash

    later or earlier timing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.70
    parsedMessage
    -0.66
    AsUp
    -0.65
     esternos
    -0.64
    исленность
    -0.64
     pères
    -0.60
     précédentes
    -0.59
     futurs
    -0.59
     anteriores
    -0.56
     Allí
    -0.55
    POSITIVE LOGITS
     than
    0.91
     THAN
    0.64
    hina
    0.63
     generations
    0.61
     stages
    0.61
     versions
    0.60
    als
    0.59
    ally
    0.59
     مرئيه
    0.59
    Revenir
    0.58
    Act Density 0.076%

    No Known Activations