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

    Neuronpedia

    INDEX
    Explanations

    possessive followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.52
    to
    0.50
    م
    0.48
     eukaryotes
    0.45
    تي
    0.44
     económicos
    0.44
    тных
    0.44
    eers
    0.43
    นั้น
    0.43
    ز
    0.43
    POSITIVE LOGITS
     생
    0.49
     been
    0.46
    ン
    0.44
    า
    0.43
    ır
    0.42
    ન
    0.40
     finest
    0.38
    ı
    0.37
     경우
    0.37
     gotta
    0.37
    Act Density 0.046%

    No Known Activations