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

    Neuronpedia

    INDEX
    Explanations

    materials, properties, and qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    妿
    0.43
     やつ
    0.43
     הר
    0.42
     ყ
    0.41
     عبدالع
    0.39
     ற
    0.39
    icions
    0.39
     ਤਾਂ
    0.38
    茁
    0.38
    ‛
    0.37
    POSITIVE LOGITS
     once
    0.51
     then
    0.46
     elite
    0.42
     randomly
    0.41
     waiting
    0.39
     properties
    0.39
    Pant
    0.39
     parton
    0.38
    MyDrive
    0.38
    cloudflare
    0.38
    Act Density 0.017%

    No Known Activations