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

    Neuronpedia

    INDEX
    Explanations

    reign of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.97
     (
    0.79
     \
    0.77
     +
    0.70
     or
    0.68
     [
    0.68
     I
    0.66
     -
    0.63
     AND
    0.63
     này
    0.61
    POSITIVE LOGITS
    শংস
    0.80
    ग्वि
    0.75
     सूत्रकृ
    0.71
    ຈັດສົ່ງ
    0.70
    ुलिस
    0.67
    abhavena
    0.65
    লাইয়া
    0.64
    ོས་
    0.64
    作者
    0.64
    被告
    0.64
    Act Density 0.000%

    No Known Activations