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

    Neuronpedia

    INDEX
    Explanations

    spacetime fabric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.44
     humor
    0.42
     оте
    0.41
    ↵↵↵↵↵
    0.41
    事务
    0.41
    urt
    0.40
    omerase
    0.40
    olog
    0.40
     where
    0.39
    ↵↵
    0.38
    POSITIVE LOGITS
     Biết
    0.49
    との
    0.49
    予算
    0.47
     Thiago
    0.46
     partie
    0.46
     hükü
    0.46
     Netflix
    0.45
    にとって
    0.45
    ന്വേഷ
    0.45
     Nasdaq
    0.44
    Act Density 0.001%

    No Known Activations