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

    Neuronpedia

    INDEX
    Explanations

    here we are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     szczególnie
    0.52
    但是在
    0.46
     खूप
    0.45
    кій
    0.45
     خصوص
    0.45
     Especial
    0.43
     केवळ
    0.42
     BECAUSE
    0.42
     allerdings
    0.41
     especial
    0.41
    POSITIVE LOGITS
     voila
    0.75
     voilà
    0.75
     bam
    0.55
    ooo
    0.51
     gedaan
    0.51
     gone
    0.50
     ecco
    0.50
     হাজির
    0.50
     presto
    0.49
    🪄
    0.49
    Act Density 0.034%

    No Known Activations