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

    Neuronpedia

    INDEX
    Explanations

    nationdifferent kinds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     twelve
    0.47
     १२
    0.46
     ১২
    0.45
    ۱۲
    0.45
     XII
    0.43
    十二
    0.43
     objets
    0.42
    हम
    0.40
     ή
    0.40
     Twelfth
    0.38
    POSITIVE LOGITS
    db
    0.38
     फाइव
    0.37
    дами
    0.36
    ンテージ
    0.36
    owered
    0.36
    deer
    0.36
    دد
    0.35
    ंडन
    0.35
    とその
    0.35
    T
    0.34
    Act Density 0.025%

    No Known Activations