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

    Neuronpedia

    INDEX
    Explanations

    at least

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಗಳಿಂದ
    0.77
     terecht
    0.66
     James
    0.64
     подряд
    0.58
     Nouvelle
    0.57
    なのですが
    0.57
    িক্ত
    0.57
    ]]);
    0.55
    James
    0.55
     ลง
    0.55
    POSITIVE LOGITS
    至少
    4.61
     atleast
    4.41
     almeno
    4.29
    少なくとも
    3.84
     mindestens
    3.51
     zumindest
    3.32
     حداقل
    3.16
     অন্তত
    3.07
     least
    2.97
     কমপক্ষে
    2.88
    Act Density 0.196%

    No Known Activations