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

    Neuronpedia

    INDEX
    Explanations

    city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    目的
    0.75
    えます
    0.74
    रियर
    0.66
    redient
    0.66
    content
    0.65
     thumbnails
    0.64
     discrete
    0.64
     congruent
    0.63
    クロマト
    0.62
     countries
    0.62
    POSITIVE LOGITS
     city
    2.40
     City
    2.35
    City
    2.16
     città
    2.04
     शहर
    2.04
    city
    2.00
     metropolitan
    1.93
     ciudad
    1.89
     Airport
    1.89
     cityscape
    1.89
    Act Density 0.447%

    No Known Activations