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

    Neuronpedia

    INDEX
    Explanations

    references to time intervals, specifically years and months

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

    Reference to a period of time

    np_acts-logits-general · gemini-2.0-flash

    years and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eeu
    -0.47
     /\.
    -0.41
    Exit
    -0.40
    Dichloroethane
    -0.40
    veau
    -0.39
    easter
    -0.39
     hour
    -0.38
    hour
    -0.38
     exited
    -0.38
     levens
    -0.37
    POSITIVE LOGITS
     spent
    1.01
    spent
    0.88
     Spent
    0.86
    parsedMessage
    0.79
     passés
    0.79
     passée
    0.78
    setVerticalGroup
    0.76
    RegressionTest
    0.74
     abroad
    0.74
     together
    0.72
    Act Density 0.219%

    No Known Activations