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

    Neuronpedia

    INDEX
    Explanations

    diet and lifestyle improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OI
    0.52
    ᱐
    0.49
    хбет
    0.49
     ειδ
    0.46
    QI
    0.46
     chaqueta
    0.45
    jj
    0.45
    ミス
    0.43
     Mạnh
    0.43
     때
    0.43
    POSITIVE LOGITS
    τή
    0.49
    逐步
    0.43
    পুণ
    0.43
    ש
    0.41
     فإن
    0.41
     easements
    0.40
    ло
    0.40
    но
    0.40
    键
    0.39
    arle
    0.39
    Act Density 0.001%

    No Known Activations