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

    Neuronpedia

    INDEX
    Explanations

    especially if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Сер
    0.51
    Ми
    0.47
    Се
    0.47
    Мар
    0.47
    Опера
    0.45
    شك
    0.44
     Spirituality
    0.44
    Education
    0.44
    Music
    0.43
    Фа
    0.43
    POSITIVE LOGITS
     avec
    0.55
     +-
    0.51
     confinement
    0.50
     high
    0.50
     moyennes
    0.49
     원하는
    0.48
    ieu
    0.47
     cellphone
    0.47
     앞
    0.47
     couche
    0.47
    Act Density 0.006%

    No Known Activations