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

    Neuronpedia

    INDEX
    Explanations

    tasks and action items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     configur
    0.55
     sauce
    0.52
     liberd
    0.49
     použí
    0.49
     infusion
    0.48
     algebras
    0.47
     polyphen
    0.47
     spacetime
    0.47
     사용하는
    0.47
     använd
    0.46
    POSITIVE LOGITS
     tasks
    0.96
    任务
    0.95
     Tasks
    0.95
    tasks
    0.94
    Tasks
    0.87
    taskList
    0.85
     завдання
    0.80
     Aufgaben
    0.80
     задачи
    0.79
     tarefas
    0.79
    Act Density 0.162%

    No Known Activations