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

    Neuronpedia

    INDEX
    Explanations

    wheel-turning, bubbly octopus, destructive device

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Blood
    0.40
    かもしれません
    0.40
    covid
    0.39
    かもしれない
    0.39
    blood
    0.39
    টাতে
    0.38
     revenues
    0.38
    Covid
    0.38
    Christmas
    0.38
    restaurant
    0.38
    POSITIVE LOGITS
    她们
    0.45
     Predictive
    0.41
    叓
    0.41
    预测
    0.41
    涷
    0.39
    周围
    0.38
    颞
    0.37
    نا
    0.37
     આવા
    0.37
    颈
    0.37
    Act Density 0.000%

    No Known Activations