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

    Neuronpedia

    INDEX
    Explanations

    conditional clauses like if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    当時
    0.49
    اي
    0.47
    time
    0.40
     percentage
    0.40
     ruck
    0.39
    當時
    0.39
     европей
    0.39
     civilian
    0.38
     соотно
    0.38
    </strong>
    0.38
    POSITIVE LOGITS
     集
    0.49
     ویک
    0.48
     如果
    0.47
    Timber
    0.47
     ProductCategory
    0.47
     Harvesting
    0.46
    )。
    0.46
     创建
    0.46
     humide
    0.46
    ম্‌
    0.46
    Act Density 0.004%

    No Known Activations