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

    Neuronpedia

    INDEX
    Explanations

    total global figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    法规
    0.39
    戽
    0.38
    运气
    0.38
     تقویت
    0.38
    进制
    0.37
    链路
    0.37
    几十
    0.37
    区别
    0.36
    证明
    0.35
    गेशन
    0.35
    POSITIVE LOGITS
     total
    1.06
    total
    0.98
     totale
    0.84
     GDP
    0.81
     annual
    0.78
     toplam
    0.75
     Total
    0.74
     মোট
    0.73
     TOTAL
    0.72
    Total
    0.71
    Act Density 0.079%

    No Known Activations