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

    Neuronpedia

    INDEX
    Explanations

    budget management and allocation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ene
    0.85
    0.82
    ного
    0.80
    는
    0.79
    ный
    0.76
    s
    0.75
    ные
    0.74
    ‌ها
    0.74
    v
    0.74
    える
    0.73
    POSITIVE LOGITS
    ي
    1.24
    ET
    1.23
    ক
    1.16
    to
    1.09
    ED
    1.04
    ER
    1.02
    ES
    1.02
    Budget
    0.98
    ל
    0.98
     for
    0.96
    Act Density 0.009%

    No Known Activations