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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     year
    0.60
    –
    0.56
    aid
    0.54
    <start_of_image>
    0.51
    year
    0.50
     calendar
    0.50
     omn
    0.49
     riz
    0.49
     calendário
    0.47
    anza
    0.47
    POSITIVE LOGITS
     不过
    0.52
     因为
    0.50
     कुनै
    0.49
     古
    0.48
     الوحد
    0.48
     đám
    0.47
     約
    0.46
     Comerc
    0.46
    blusas
    0.46
     Verification
    0.46
    Act Density 0.004%

    No Known Activations