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

    Neuronpedia

    INDEX
    Explanations

    tasks and automation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     функциони
    1.14
     funcionamento
    1.00
     műkö
    0.98
     funcionamiento
    0.97
     funkcjon
    0.95
    働
    0.94
     functioning
    0.93
     użyt
    0.92
    働く
    0.92
    functioning
    0.91
    POSITIVE LOGITS
     tasks
    2.04
     Tasks
    1.98
    Tasks
    1.76
     task
    1.75
    Task
    1.74
    tasks
    1.69
     Task
    1.65
     tarefa
    1.59
     tarefas
    1.57
     задачи
    1.54
    Act Density 0.215%

    No Known Activations