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

    Neuronpedia

    INDEX
    Explanations

    past tense actions followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.64
     chce
    0.62
     ہے
    0.60
     obecnie
    0.59
    今の
    0.57
     your
    0.55
     você
    0.54
     është
    0.54
     são
    0.53
     pouco
    0.53
    POSITIVE LOGITS
    當時
    0.96
    当时
    0.95
     damals
    0.88
     damal
    0.83
     ήταν
    0.77
    当時
    0.77
     وكان
    0.75
     بودند
    0.74
     volna
    0.74
     ছিল
    0.73
    Act Density 0.131%

    No Known Activations