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

    Neuronpedia

    INDEX
    Explanations

    birth control and birth rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.29
    .
    1.23
    ла
    1.18
    л
    1.10
    é
    1.08
    મ
    1.02
    ul
    1.01
    った
    1.00
    ва
    0.97
    ס
    0.96
    POSITIVE LOGITS
     Birth
    1.21
    birth
    1.18
     birth
    1.11
    ll
    0.82
    д
    0.80
    d
    0.80
    h
    0.79
    د
    0.79
    s
    0.78
     lahir
    0.76
    Act Density 0.004%

    No Known Activations