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

    Neuronpedia

    INDEX
    Explanations

    day before or day of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sol
    0.36
    antian
    0.36
    항
    0.35
    泥
    0.34
     percib
    0.34
     nontrivial
    0.34
     implication
    0.33
    ادرات
    0.33
     aliqua
    0.33
    мум
    0.33
    POSITIVE LOGITS
    当日
    1.40
    当天
    1.35
     day
    1.19
     день
    1.05
     يوم
    1.00
     giorno
    0.95
     Day
    0.95
     সেদিন
    0.95
     அன்று
    0.94
     dniu
    0.94
    Act Density 0.013%

    No Known Activations