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

    Neuronpedia

    INDEX
    Explanations

    infinitive marker "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    В
    0.61
    Р
    0.53
     red
    0.50
     $
    0.45
    وز
    0.44
    Al
    0.44
     all
    0.44
    ่าง
    0.43
     chiropractor
    0.42
    Л
    0.42
    POSITIVE LOGITS
     জনপ্র
    0.52
     Fmat
    0.46
     പേ
    0.46
    0.46
    otiti
    0.44
    टरी
    0.44
    popupIsOpen
    0.43
    口气
    0.43
     Confucian
    0.42
     తమి
    0.42
    Act Density 0.002%

    No Known Activations