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

    Neuronpedia

    INDEX
    Explanations

    car safety technology

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vehicles
    0.83
     voiture
    0.79
     মোটরসাই
    0.77
    汽車
    0.76
     automóviles
    0.75
     cars
    0.75
     السيارات
    0.75
     voitures
    0.74
     വാഹന
    0.74
    Veh
    0.73
    POSITIVE LOGITS
     Dias
    0.70
     dias
    0.70
     ECA
    0.66
    peg
    0.65
    Dias
    0.63
     Kip
    0.63
     শহর
    0.63
     Cook
    0.63
     apron
    0.63
     EPA
    0.63
    Act Density 0.035%

    No Known Activations