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

    Neuronpedia

    INDEX
    Explanations

    tasks and schedules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yılında
    0.38
    tahun
    0.37
    वर्षी
    0.36
     aastal
    0.35
     ironic
    0.34
     Roder
    0.34
     peuple
    0.34
     katalog
    0.34
     aast
    0.34
     bullying
    0.34
    POSITIVE LOGITS
     snacks
    0.53
     workday
    0.53
     Snacks
    0.52
     Snack
    0.50
    出门
    0.50
     snack
    0.49
    Lunch
    0.49
     lunchtime
    0.49
     दोपहर
    0.48
     midday
    0.48
    Act Density 0.337%

    No Known Activations