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

    Neuronpedia

    INDEX
    Explanations

    limited precision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     рас
    0.44
     Moral
    0.43
     небе
    0.43
     опера
    0.42
     Memorandum
    0.42
     hereby
    0.42
    幸运
    0.41
    コーナー
    0.40
     корпу
    0.40
     Coordinates
    0.40
    POSITIVE LOGITS
     comparability
    0.45
     também
    0.42
     picking
    0.42
    டனும்
    0.42
    なども
    0.42
     tambien
    0.42
     quizá
    0.41
    بھی
    0.41
     marrying
    0.39
     nigg
    0.39
    Act Density 0.004%

    No Known Activations