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

    Neuronpedia

    INDEX
    Explanations

    list of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dail
    0.48
     Shakespeare
    0.47
     Scand
    0.46
     fax
    0.46
     email
    0.46
    貶
    0.45
     Bank
    0.45
    িউ
    0.45
     Nasdaq
    0.45
    ரு
    0.44
    POSITIVE LOGITS
    ول
    0.54
     می‌
    0.52
     कैंडिडेट्स
    0.50
    Figs
    0.49
    Всім
    0.48
    Après
    0.47
     جایی
    0.47
    Ratings
    0.46
    Alles
    0.45
     بعض
    0.45
    Act Density 0.002%

    No Known Activations