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

    Neuronpedia

    INDEX
    Explanations

    leukemia, lease, leopard, leaching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ago
    0.42
     माल
    0.41
     மாதிர
    0.40
     conseguenza
    0.40
     প্রাক্তন
    0.39
    expec
    0.39
     {}",
    0.38
     اخر
    0.38
    ยอด
    0.38
     மாதிரி
    0.38
    POSITIVE LOGITS
    Le
    0.78
     Le
    0.70
     lej
    0.62
     le
    0.56
     ле
    0.54
     Ле
    0.54
     LE
    0.53
     leve
    0.53
     레
    0.52
     leaching
    0.49
    Act Density 0.013%

    No Known Activations