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

    Neuronpedia

    INDEX
    Explanations

    asap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puedes
    0.42
     अधिकांश
    0.41
     მნიშვნელ
    0.40
     często
    0.40
     سپس
    0.40
     ಬೀ
    0.39
     बहुतेक
    0.38
     egiten
    0.38
     spesso
    0.37
     позволяет
    0.37
    POSITIVE LOGITS
     someday
    0.52
    尽快
    0.52
     möglichst
    0.49
     asap
    0.49
     хочет
    0.48
     ASAP
    0.43
    인데
    0.42
    зить
    0.41
    或者是
    0.41
     хочу
    0.40
    Act Density 0.197%

    No Known Activations