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

    Neuronpedia

    INDEX
    Explanations

    days and schedules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tickets
    0.86
    ırken
    0.85
     jedes
    0.83
     strollers
    0.82
     διάρκ
    0.82
    ameras
    0.82
     durations
    0.82
     attracts
    0.82
    Tickets
    0.81
     stipulates
    0.80
    POSITIVE LOGITS
     cleanup
    1.02
     день
    0.97
    cleanup
    0.88
     Cleanup
    0.88
     day
    0.85
    푹
    0.84
     cleaning
    0.84
    再び
    0.84
     रिवीजन
    0.80
    今日は
    0.80
    Act Density 0.203%

    No Known Activations