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

    Neuronpedia

    INDEX
    Explanations

    slightly, subtle variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الدین
    0.48
    ファスナー
    0.44
     سنی
    0.42
    ן
    0.41
     Assertion
    0.40
    aped
    0.40
    UnitTest
    0.39
     발견
    0.39
    Wyn
    0.39
     Cott
    0.38
    POSITIVE LOGITS
     slight
    0.58
     breeze
    0.58
     variations
    0.57
    y
    0.57
     breezes
    0.56
     differences
    0.55
     nuances
    0.54
     subtly
    0.51
     difference
    0.50
    不同的
    0.50
    Act Density 0.019%

    No Known Activations