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

    Neuronpedia

    INDEX
    Explanations

    location, size, and shape properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    സ്
    0.98
    nya
    0.96
    ката
    0.91
    ংখ্যান
    0.89
    ophones
    0.88
    ക്ക്
    0.88
    湖南
    0.87
    শকার
    0.87
    ELO
    0.86
    ल्यावर
    0.86
    POSITIVE LOGITS
    ে
    1.10
    擷
    1.02
     sueño
    0.96
     început
    0.96
     ügy
    0.95
    ptăm
    0.93
    ({'
    0.91
     stvar
    0.91
     musia
    0.89
     unsustainable
    0.89
    Act Density 0.001%

    No Known Activations