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

    Neuronpedia

    INDEX
    Explanations

    Google presentation context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чер
    0.49
    ัด
    0.47
    idity
    0.45
    ot
    0.45
    шал
    0.45
    ли
    0.44
    ц
    0.44
    ంగా
    0.44
    ونت
    0.44
     planned
    0.43
    POSITIVE LOGITS
     Pakistan
    0.45
     sürec
    0.44
     만들
    0.44
     Küçük
    0.43
    वसु
    0.43
    ইতি
    0.43
     اولین
    0.42
    天津
    0.41
     avviene
    0.41
    儼
    0.41
    Act Density 0.001%

    No Known Activations