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

    Neuronpedia

    INDEX
    Explanations

    followed by proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ')
    0.52
    р
    0.52
     사는
    0.50
     sẽ
    0.48
    ")
    0.47
     ไม่
    0.47
    />
    0.45
     coincides
    0.45
     begs
    0.45
    '),
    0.45
    POSITIVE LOGITS
     tzw
    0.65
    👲
    0.62
     isang
    0.62
     tradisional
    0.60
     militari
    0.60
     tzv
    0.59
     dermatology
    0.56
     colonialism
    0.55
     thermocou
    0.54
     właścic
    0.54
    Act Density 2.939%

    No Known Activations