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

    Neuronpedia

    INDEX
    Explanations

    m-starting non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paradigma
    0.42
    Minn
    0.41
    MMM
    0.41
    粓
    0.41
     Magnum
    0.40
     bilhões
    0.39
     catholique
    0.39
     النموذج
    0.39
    GPa
    0.38
    minas
    0.38
    POSITIVE LOGITS
     Μ
    0.51
     mə
    0.49
     mettre
    0.48
     মোট
    0.46
     με
    0.46
     měla
    0.46
     мы
    0.45
     меня
    0.45
     မ
    0.44
     mão
    0.44
    Act Density 0.559%

    No Known Activations