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

    Neuronpedia

    INDEX
    Explanations

    can / could after pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Expect
    0.76
    രിച്ചത്
    0.75
     હશે
    0.74
    াবের
    0.70
    രിക്കുന്നത്
    0.70
     ሰዎች
    0.70
    രുന്നത്
    0.68
     youll
    0.67
     باشید
    0.67
    当你
    0.66
    POSITIVE LOGITS
     can
    4.29
    can
    3.76
     Can
    3.56
    Can
    3.50
     можно
    3.42
    可以
    3.35
     можна
    3.29
     dapat
    3.29
     could
    3.24
     bisa
    3.14
    Act Density 1.199%

    No Known Activations