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

    Neuronpedia

    INDEX
    Explanations

    names of mythological figures and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blushed
    0.48
     startled
    0.48
     surprised
    0.47
    0.46
     unexpected
    0.46
    더라도
    0.46
     queer
    0.46
     dainty
    0.46
     less
    0.45
     Unexpected
    0.45
    POSITIVE LOGITS
    สำหรับการ
    0.61
    សម្រាប់ការ
    0.59
     우리가
    0.54
     სისტ
    0.53
    战争
    0.52
    businessman
    0.51
    bitcoin
    0.51
    sistema
    0.50
     funzionamento
    0.50
     для
    0.50
    Act Density 0.013%

    No Known Activations