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

    Neuronpedia

    INDEX
    Explanations

    references to time durations and effort in activities

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

    amounts of time

    np_acts-logits-general · gemini-2.0-flash

    working hours and nights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rodea
    -0.41
    ječ
    -0.35
     cucchiaio
    -0.34
     próxima
    -0.33
     aarde
    -0.31
    fahrer
    -0.31
     Publik
    -0.31
     confidence
    -0.31
     soon
    -0.30
    ływ
    -0.30
    POSITIVE LOGITS
    StructEnd
    0.75
     hours
    0.73
     overtime
    0.71
    hours
    0.70
     kasarigan
    0.69
     Hours
    0.68
     utafitiHapana
    0.68
    Hours
    0.67
     للاسماء
    0.66
    nights
    0.65
    Act Density 0.239%

    No Known Activations