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

    Neuronpedia

    INDEX
    Explanations

    csv, UseCase, Almighty, dt, demo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infrast
    0.54
     Work
    0.50
     Infrastructure
    0.49
     Chiang
    0.49
    schnitt
    0.49
     Yangtze
    0.49
    tr
    0.48
     Brussel
    0.47
     Smaller
    0.47
     Guill
    0.47
    POSITIVE LOGITS
    éléments
    0.52
    로
    0.47
    otides
    0.45
    ที่
    0.44
     glories
    0.42
    집
    0.42
    的情况
    0.42
    ళ్ళ
    0.42
    회
    0.42
    푐
    0.42
    Act Density 0.001%

    No Known Activations