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

    Neuronpedia

    INDEX
    Explanations

    know your meme

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ير
    0.41
     know
    0.39
     infiltrate
    0.37
     जानते
    0.37
    知道
    0.36
     знаем
    0.36
     zna
    0.36
     জানেন
    0.35
     kennen
    0.35
    丄
    0.35
    POSITIVE LOGITS
     what
    0.50
    what
    0.48
     व्हाट
    0.42
     everything
    0.39
    how
    0.39
    downs
    0.38
    everything
    0.38
     whats
    0.37
    berry
    0.36
     địch
    0.36
    Act Density 0.004%

    No Known Activations