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

    Neuronpedia

    INDEX
    Explanations

    often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     හා
    1.23
    居然
    1.23
    也许
    1.22
     וה
    1.19
     semoga
    1.18
    其實
    1.18
     البته
    1.17
     дори
    1.17
    也許
    1.16
     പോലും
    1.14
    POSITIVE LOGITS
    mals
    1.08
    ifiably
    1.05
     been
    1.05
     été
    1.00
     quite
    0.87
     be
    0.86
     have
    0.86
     proceeded
    0.85
     went
    0.80
     served
    0.79
    Act Density 0.445%

    No Known Activations