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

    Neuronpedia

    INDEX
    Explanations

    foreign languages or common prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    作者
    0.47
    Student
    0.43
    没有任何
    0.43
    并非
    0.42
     学生
    0.42
     taskId
    0.40
    Author
    0.39
     oscillates
    0.39
    学生
    0.38
     STUDENT
    0.38
    POSITIVE LOGITS
     ab
    0.41
     delle
    0.39
     en
    0.39
     sono
    0.39
    ci
    0.38
     tras
    0.38
     вот
    0.38
     sette
    0.38
    tho
    0.37
     quais
    0.37
    Act Density 0.000%

    No Known Activations