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

    Neuronpedia

    INDEX
    Explanations

    technical and narrative contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hero
    0.45
    udp
    0.44
    ede
    0.43
     CFI
    0.43
     Pasta
    0.43
    shares
    0.43
    ayan
    0.43
    olesale
    0.43
    toy
    0.43
     Carpet
    0.43
    POSITIVE LOGITS
     liée
    0.55
     причем
    0.48
     ferrugineux
    0.45
     además
    0.44
    जा
    0.44
     inwon
    0.43
     that
    0.43
     llena
    0.43
     sebesar
    0.42
     حنا
    0.42
    Act Density 0.003%

    No Known Activations