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

    Neuronpedia

    INDEX
    Explanations

    gratification and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    时期
    0.48
    సి
    0.47
    马
    0.46
     unimagin
    0.46
    土
    0.45
    比
    0.44
    ప్ర
    0.44
    时间内
    0.44
    スイーツ
    0.44
    国
    0.43
    POSITIVE LOGITS
    ila
    0.56
     त्यांचे
    0.55
    icha
    0.54
    esta
    0.52
    ulia
    0.52
     nobis
    0.52
    bam
    0.50
     рез
    0.50
    roga
    0.50
     ваш
    0.49
    Act Density 0.000%

    No Known Activations