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

    Neuronpedia

    INDEX
    Explanations

    academic degrees and education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tarefa
    0.83
     firmy
    0.83
     tarefas
    0.77
    Clientes
    0.76
     clientes
    0.76
     कार्यकर्ताओं
    0.75
    任务
    0.75
    TASK
    0.74
     Verantwort
    0.74
     tarea
    0.74
    POSITIVE LOGITS
     degree
    2.38
     degrees
    2.22
     Degree
    2.11
    degree
    2.08
    Degree
    2.04
     graduate
    2.02
     Bachelor
    1.92
     undergraduate
    1.87
    degrees
    1.84
     Degrees
    1.78
    Act Density 0.428%

    No Known Activations