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

    Neuronpedia

    INDEX
    Explanations

    past, were

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    1.90
     ఉంటుంది
    1.80
     βρίσκεται
    1.78
     është
    1.72
     చేస్తుంది
    1.66
     является
    1.66
     заключается
    1.61
     isn
    1.61
     ہے
    1.58
     γίνεται
    1.57
    POSITIVE LOGITS
     were
    4.58
    were
    3.95
     weren
    3.83
     WERE
    3.36
     Were
    3.36
    Were
    3.36
     بودند
    3.34
     erano
    3.29
     furono
    3.26
     waren
    3.24
    Act Density 0.246%

    No Known Activations