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

    Neuronpedia

    INDEX
    Explanations

    * **the** embedding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seemed
    0.41
    pho
    0.41
    शुदा
    0.40
    fried
    0.39
     veggies
    0.39
     coffin
    0.39
     wou
    0.39
     veggie
    0.39
    coff
    0.39
     //.
    0.38
    POSITIVE LOGITS
     গুণ
    0.47
    循環
    0.43
    ग्राह
    0.43
     நு
    0.41
     continuidade
    0.39
    制御
    0.38
    템
    0.38
    நு
    0.38
    均衡
    0.38
    閬
    0.38
    Act Density 0.000%

    No Known Activations