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

    Neuronpedia

    INDEX
    Explanations

    references to time, particularly the concept of "years."

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

    "Years" or time-related contexts

    np_acts-logits-general · gemini-2.0-flash

    over the years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTS
    -0.40
     READY
    -0.39
     ready
    -0.39
    ]--;
    -0.39
    孤
    -0.38
    Intr
    -0.38
     esimer
    -0.38
     assolutamente
    -0.37
    了嗎
    -0.37
    ветить
    -0.37
    POSITIVE LOGITS
     years
    0.82
     åren
    0.68
     Years
    0.66
    RegressionTest
    0.66
    years
    0.65
    Years
    0.63
     days
    0.62
     годы
    0.60
    évaluateur
    0.60
     latach
    0.60
    Act Density 0.175%

    No Known Activations