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

    Neuronpedia

    INDEX
    Explanations

    the more, the more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     혹은
    0.45
    knn
    0.42
    合せ
    0.41
     ឬ
    0.40
    Ϻ
    0.39
     અથવા
    0.38
    䂧
    0.38
     किंवा
    0.37
    ():
    0.36
    навли
    0.36
    POSITIVE LOGITS
    越多
    1.02
    越高
    0.91
    越大
    0.90
    수록
    0.89
     desto
    0.80
     जितना
    0.80
     càng
    0.77
    ยิ่ง
    0.74
     ততই
    0.74
     যত
    0.70
    Act Density 0.115%

    No Known Activations