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

    Neuronpedia

    INDEX
    Explanations

    time periods and intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overnight
    0.63
     weekend
    0.62
     weekends
    0.62
     diarias
    0.58
    weekend
    0.55
     dni
    0.51
     Wochenende
    0.51
     daily
    0.49
     sleepless
    0.49
     days
    0.49
    POSITIVE LOGITS
     warmup
    0.61
    分钟
    0.58
    Minutes
    0.55
     startTime
    0.54
    Warm
    0.54
     intermission
    0.54
    休憩
    0.54
     Minutes
    0.52
     minutes
    0.52
     মিনিট
    0.51
    Act Density 0.199%

    No Known Activations