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

    Neuronpedia

    INDEX
    Explanations

    gross salary, profit, wages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Params
    0.55
    u
    0.55
    ്യ
    0.54
    Current
    0.53
     anxiously
    0.52
    のス
    0.52
    STANDING
    0.51
    𝚊
    0.51
     pdelay
    0.50
    ளைஞ
    0.50
    POSITIVE LOGITS
     gross
    0.95
     net
    0.70
     Gross
    0.68
    Gross
    0.65
     bruto
    0.59
     Net
    0.58
     crude
    0.58
     netto
    0.58
     kasar
    0.58
    粗
    0.57
    Act Density 0.027%

    No Known Activations