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

    Neuronpedia

    INDEX
    Explanations

    university buildings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resultArray
    0.40
    জিওথের
    0.40
     Structured
    0.39
     書い
    0.37
    த்துள்ள
    0.37
    fieldContext
    0.37
    த்திரை
    0.37
    terase
    0.36
    胯
    0.36
    <unused42>
    0.36
    POSITIVE LOGITS
     buildings
    0.73
     main
    0.68
     building
    0.68
     Main
    0.66
    Main
    0.65
     bâtiment
    0.64
     건물
    0.64
    Buildings
    0.62
     edificio
    0.61
     Building
    0.60
    Act Density 0.001%

    No Known Activations