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

    Neuronpedia

    INDEX
    Explanations

    it's contraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我是
    0.35
     happily
    0.35
     gladly
    0.34
     নিচ্ছে
    0.34
     इसने
    0.32
     haberse
    0.31
     proudly
    0.30
     incarcer
    0.30
     করেনি
    0.30
    γγ
    0.29
    POSITIVE LOGITS
    િમ
    0.30
      
    0.28
    价
    0.27
    erate
    0.27
     principle
    0.26
    》。
    0.26
    '
    0.26
    ruitment
    0.26
     Maul
    0.26
    ivided
    0.26
    Act Density 0.037%

    No Known Activations