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

    Neuronpedia

    INDEX
    Explanations

    Indian cities and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     idk
    0.54
     পুনরায়
    0.52
     undesired
    0.50
    Yeah
    0.49
    Upon
    0.49
     বাহিরে
    0.49
     freaking
    0.48
     dystopian
    0.48
     underwhelming
    0.48
    TikTok
    0.48
    POSITIVE LOGITS
     Bangalore
    0.77
     Gurgaon
    0.76
     Mumbai
    0.76
     Chennai
    0.76
     Maharashtra
    0.73
     Maruti
    0.70
     Karnataka
    0.68
     Andhra
    0.67
     mumbai
    0.67
    Incidentally
    0.67
    Act Density 0.001%

    No Known Activations