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

    Neuronpedia

    INDEX
    Explanations

    templates and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     керу
    0.46
    ження
    0.44
    sill
    0.44
    řez
    0.44
    슥
    0.44
     жо
    0.42
     Resin
    0.42
    ieważ
    0.42
    seudo
    0.42
    落实
    0.42
    POSITIVE LOGITS
     en
    0.55
     nightlife
    0.46
     double
    0.46
     slums
    0.44
     slum
    0.44
     También
    0.44
     cityscape
    0.43
     Past
    0.43
     reserve
    0.43
     city
    0.42
    Act Density 0.001%

    No Known Activations