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

    Neuronpedia

    INDEX
    Explanations

    метеоролог, метод

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mech
    0.39
    ester
    0.39
    ^{*}$-
    0.38
    ัติ
    0.38
     मी
    0.37
     bok
    0.37
     গণ্য
    0.37
    ივ
    0.37
    ικής
    0.36
    ան
    0.36
    POSITIVE LOGITS
    тод
    0.45
    цена
    0.41
    тори
    0.41
    Ross
    0.40
     النق
    0.40
     داع
    0.40
    дея
    0.40
    மொழி
    0.39
    дали
    0.39
    риди
    0.39
    Act Density 0.002%

    No Known Activations