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

    Neuronpedia

    INDEX
    Explanations

    defining concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jaff
    0.43
     éventuellement
    0.42
    㭐
    0.41
    귿
    0.40
    ✽
    0.39
     Lesotho
    0.39
    iple
    0.39
     Paglinawan
    0.39
    こうした
    0.39
    ण्ड
    0.38
    POSITIVE LOGITS
     objetos
    0.50
     belleza
    0.47
     disfruta
    0.46
    ING
    0.45
     vib
    0.45
     disfrutar
    0.45
     trova
    0.44
     estaría
    0.44
     l
    0.43
     parece
    0.43
    Act Density 0.002%

    No Known Activations