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

    Neuronpedia

    INDEX
    Explanations

    who followed by auxiliary verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terjadi
    0.37
     โรง
    0.36
     व्रत
    0.36
     ermöglichen
    0.35
     Temple
    0.33
     רק
    0.33
     Notebook
    0.33
     SII
    0.32
    梓
    0.32
     আকাশ
    0.31
    POSITIVE LOGITS
     whom
    0.59
    whom
    0.57
     owns
    0.56
    Who
    0.52
     else
    0.51
     who
    0.50
     knows
    0.50
     Who
    0.50
     governs
    0.49
     Whom
    0.49
    Act Density 0.015%

    No Known Activations