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

    Neuronpedia

    INDEX
    Explanations

    Okay, you want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    })^{-
    0.46
     শেষ
    0.42
     setActive
    0.42
     최종
    0.42
     THEN
    0.40
    хом
    0.40
    スマホ
    0.39
    OutSize
    0.39
     рамках
    0.38
     Stark
    0.38
    POSITIVE LOGITS
    Concern
    0.43
    bergen
    0.43
     debating
    0.41
    Fra
    0.40
    National
    0.39
    Educational
    0.39
    Titles
    0.39
    Commit
    0.39
     शैक्षिक
    0.39
     assuntos
    0.38
    Act Density 0.003%

    No Known Activations