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

    Neuronpedia

    INDEX
    Explanations

    stargate sg-1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infuse
    0.47
    蝌
    0.46
     composure
    0.45
     strenuous
    0.45
     elevate
    0.44
     retirer
    0.43
     createFile
    0.43
    PPE
    0.43
    佬
    0.42
     gooey
    0.41
    POSITIVE LOGITS
     и
    0.58
    в
    0.50
    ار
    0.47
     идет
    0.46
    (
    0.45
     Baran
    0.45
     Galbraith
    0.45
    Ὁ
    0.44
     последнего
    0.44
    рда
    0.44
    Act Density 0.000%

    No Known Activations