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

    Neuronpedia

    INDEX
    Explanations

    references to time-related phrases or time intervals

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

    time units before or after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bomberos
    -0.46
     peuples
    -0.41
     particuliers
    -0.40
     enfans
    -0.40
     touristique
    -0.38
     intéress
    -0.38
     boyunca
    -0.38
     âmes
    -0.38
     ouvriers
    -0.37
     dieux
    -0.36
    POSITIVE LOGITS
    AntiForgeryToken
    0.65
    makeConstraints
    0.61
     StatelessWidget
    0.59
     instants
    0.59
    RegressionTest
    0.56
    PreferredItem
    0.56
    わずか
    0.54
    buzo
    0.53
     shortly
    0.52
    PreExecute
    0.52
    Act Density 0.008%

    No Known Activations