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

    Neuronpedia

    INDEX
    Explanations

    change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.46
    </th>
    0.46
    \}.
    0.45
    ی
    0.44
     পর্যায়ের
    0.44
     مشکلات
    0.43
    Gs
    0.43
     ยัง
    0.43
     اقدامات
    0.42
     nanofibers
    0.42
    POSITIVE LOGITS
     Change
    0.86
    改变
    0.84
     ändern
    0.81
     changé
    0.81
     Changing
    0.79
     schimb
    0.79
    Change
    0.78
     change
    0.77
     cambiato
    0.75
    válto
    0.75
    Act Density 0.120%

    No Known Activations