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

    Neuronpedia

    INDEX
    Explanations

    uwu speak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িনবার্গ
    0.48
    صالات
    0.46
    ผู้ชมในสนาม
    0.46
    靘
    0.45
    蹼
    0.45
    樘
    0.45
    鵃
    0.44
     ظِلِّ
    0.44
    贰章
    0.44
    0.44
    POSITIVE LOGITS
    Explanation
    0.79
    Answer
    0.69
     brain
    0.66
     Brain
    0.66
    ꧁
    0.66
     Explanation
    0.65
     explanation
    0.63
     Answer
    0.63
     plz
    0.63
     answer
    0.60
    Act Density 0.002%

    No Known Activations