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

    Neuronpedia

    INDEX
    Explanations

    activities or tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ølge
    0.73
     প্রমুখ
    0.70
    raiser
    0.67
    orld
    0.66
    죠
    0.66
    or
    0.64
    ↵↵↵
    0.61
    ue
    0.61
    bearer
    0.60
    ussie
    0.60
    POSITIVE LOGITS
     tarefas
    1.02
     pracuje
    0.84
     tareas
    0.81
     trabaja
    0.80
     apresenta
    0.80
     housework
    0.79
     dificultad
    0.78
    工作中
    0.75
     latihan
    0.74
     trabalha
    0.74
    Act Density 0.024%

    No Known Activations