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

    Neuronpedia

    INDEX
    Explanations

    eggs, sex, and server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     них
    0.49
     hydroxide
    0.47
    郄
    0.46
     шла
    0.43
     पेंगे
    0.42
     సమస్య
    0.42
     passivation
    0.42
     для
    0.42
     برای
    0.42
     проблем
    0.42
    POSITIVE LOGITS
    k
    0.48
     eloku
    0.47
    v
    0.45
    ahraga
    0.42
     liberd
    0.42
     ktorá
    0.42
    ائ
    0.42
     arada
    0.41
    my
    0.41
    ona
    0.41
    Act Density 0.018%

    No Known Activations