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

    Neuronpedia

    INDEX
    Explanations

    cost savings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     провести
    0.41
    CodeableConcept
    0.41
    ahmatullahi
    0.40
    MATCH
    0.40
     abbreviated
    0.38
     haste
    0.38
     المختلفة
    0.38
    CEEDINGS
    0.37
    MEA
    0.36
    igarh
    0.35
    POSITIVE LOGITS
     costs
    0.64
     koszt
    0.62
     비용
    0.61
     expenses
    0.60
     biaya
    0.57
     coût
    0.56
     coûts
    0.56
     cost
    0.55
     Costs
    0.54
     expensive
    0.54
    Act Density 0.049%

    No Known Activations