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

    Neuronpedia

    INDEX
    Explanations

    best records and averages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     своей
    0.45
     svoj
    0.42
     своего
    0.42
    🟧
    0.40
    மக்கு
    0.38
     Cine
    0.38
    ateľ
    0.38
     مورد
    0.37
     ресурсов
    0.37
     svoju
    0.37
    POSITIVE LOGITS
    students
    0.44
    Students
    0.43
     students
    0.42
     학생들이
    0.39
    MZ
    0.38
    <tr>
    0.38
     STUDENTS
    0.38
    kW
    0.37
    Record
    0.36
    傅
    0.36
    Act Density 0.001%

    No Known Activations