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

    Neuronpedia

    INDEX
    Explanations

    cost reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thoroughbred
    0.47
    ZY
    0.40
    CEEDINGS
    0.40
    MEA
    0.40
     thorough
    0.39
     excellence
    0.39
     abandonment
    0.39
     easily
    0.38
     standardization
    0.38
    YT
    0.38
    POSITIVE LOGITS
     coûts
    0.42
     biaya
    0.42
    聒
    0.41
     coûte
    0.41
     ekonom
    0.41
     비용
    0.40
    Independence
    0.39
     autonomia
    0.39
     econôm
    0.39
     پیسے
    0.38
    Act Density 0.100%

    No Known Activations