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

    Neuronpedia

    INDEX
    Explanations

    electromagnetism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     succulents
    0.80
     राघव
    0.77
     Gillespie
    0.76
     Overwatch
    0.76
     inbox
    0.75
     alve
    0.75
     Shasta
    0.74
    jorie
    0.73
    🍑
    0.72
    व्स
    0.72
    POSITIVE LOGITS
     magnetic
    3.54
     Magnetic
    3.34
    Magnetic
    3.25
     magnet
    3.22
    magnetic
    3.11
    磁
    3.10
     magnets
    3.09
     Magnet
    3.01
     magnetism
    2.90
    Magnet
    2.90
    Act Density 0.226%

    No Known Activations