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

    Neuronpedia

    INDEX
    Explanations

    electrical fuses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hej
    0.40
     quảng
    0.39
    纜
    0.39
    Montana
    0.39
    tono
    0.38
     vznik
    0.38
    っぱり
    0.38
     返
    0.38
     الحديث
    0.38
    錨
    0.38
    POSITIVE LOGITS
     fuses
    1.20
     fuse
    1.09
     Fuse
    0.93
    Fuse
    0.86
    fuse
    0.86
     fusible
    0.84
     fusing
    0.84
     fus
    0.79
     blown
    0.77
     Fus
    0.72
    Act Density 0.008%

    No Known Activations