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

    Neuronpedia

    INDEX
    Explanations

    activated during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পুস্ত
    0.70
     جلس
    0.68
     تعلم
    0.67
     trusting
    0.66
     ملا
    0.65
    readLine
    0.64
     كيلو
    0.63
     современного
    0.63
     taxonomy
    0.63
    提取
    0.62
    POSITIVE LOGITS
    urr
    0.71
     upheaval
    0.70
     fpr
    0.67
     ฟ้า
    0.67
     averted
    0.67
     ovation
    0.65
    uales
    0.65
    贱
    0.64
    
    0.61
     बाकी
    0.61
    Act Density 0.001%

    No Known Activations