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

    Neuronpedia

    INDEX
    Explanations

    company names and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     their
    0.39
     loro
    0.38
     lecture
    0.38
     appear
    0.37
    {$
    0.36
     seem
    0.36
     appeared
    0.35
     seemed
    0.35
     actual
    0.35
    他们
    0.35
    POSITIVE LOGITS
     சார்பில்
    0.57
    에서는
    0.52
    這邊
    0.52
     তরফে
    0.52
     мы
    0.50
     хочет
    0.49
     можем
    0.48
    这边
    0.48
     เรา
    0.47
     কর্তৃক
    0.47
    Act Density 0.016%

    No Known Activations