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

    Neuronpedia

    INDEX
    Explanations

    time periods or points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myBuilder
    0.40
     Jahr
    0.35
     يحت
    0.35
     Biochemical
    0.34
     自
    0.34
     ira
    0.33
     slight
    0.33
     centrifugal
    0.33
    형
    0.33
     gì
    0.32
    POSITIVE LOGITS
     bedtime
    1.11
     runtime
    1.03
     playtime
    1.01
     dinn
    1.01
     payday
    0.96
     lunchtime
    0.88
     crunch
    0.80
    runtime
    0.79
     halftime
    0.73
     downtime
    0.72
    Act Density 0.042%

    No Known Activations