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

    Neuronpedia

    INDEX
    Explanations

    modal verbs for links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     camp
    0.67
    țe
    0.61
     mon
    0.60
     intellectual
    0.60
     Mon
    0.60
    തെന്ന്
    0.60
     Xen
    0.60
     والك
    0.58
     интеллектуа
    0.57
     そこ
    0.57
    POSITIVE LOGITS
     may
    1.39
     might
    1.37
    could
    1.34
     could
    1.33
     COULD
    1.32
     ought
    1.32
    might
    1.28
     shall
    1.24
     Could
    1.22
    may
    1.21
    Act Density 0.038%

    No Known Activations