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

    Neuronpedia

    INDEX
    Explanations

    pronoun followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其他
    0.66
     lorsque
    0.66
     amelyek
    0.64
     подходя
    0.61
     demás
    0.61
     其他
    0.61
    的其他
    0.58
    From
    0.57
     اخرى
    0.56
    我认为
    0.56
    POSITIVE LOGITS
     can
    1.02
     owes
    1.01
     may
    1.01
     thrives
    0.97
     owns
    0.97
     lacks
    0.97
     seems
    0.96
     has
    0.95
     hasn
    0.95
     is
    0.95
    Act Density 0.341%

    No Known Activations