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

    Neuronpedia

    INDEX
    Explanations

    task and work-related terms in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.62
    4
    0.49
    body
    0.48
    3
    0.47
    https
    0.44
    :
    0.44
    .
    0.43
    9
    0.43
    7
    0.43
    ↵
    0.42
    POSITIVE LOGITS
     αποτε
    0.50
     задача
    0.50
     внешней
    0.49
     tarea
    0.46
    箭头
    0.46
     tarefa
    0.45
    崤
    0.45
     Ergebn
    0.44
    WeekDates
    0.44
     تشکیل
    0.44
    Act Density 0.030%

    No Known Activations