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

    Neuronpedia

    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    倫
    -0.09
     polished
    -0.08
     meteen
    -0.08
    铜
    -0.08
     Bauern
    -0.08
     cobre
    -0.07
     подходит
    -0.07
     mince
    -0.07
     художе
    -0.07
    GORITHM
    -0.07
    POSITIVE LOGITS
     exorbit
    0.13
     coûts
    0.12
     costs
    0.12
     costos
    0.12
     expenditures
    0.12
    费用
    0.11
     gasto
    0.11
     비용
    0.11
     ખર્ચ
    0.11
     bill
    0.11
    Act Density 0.021%

    No Known Activations