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

    Neuronpedia

    INDEX
    Explanations

    foreign key constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     τραγ
    0.47
    漢字
    0.43
    ྨ
    0.43
    ológico
    0.40
    바
    0.40
    пка
    0.40
     कामया
    0.39
     músicos
    0.39
    예
    0.38
    🤒
    0.38
    POSITIVE LOGITS
    Constraint
    0.51
     constraining
    0.50
     Constraint
    0.48
     constraint
    0.46
     respectful
    0.46
     imposed
    0.45
     constrain
    0.44
    Respect
    0.44
     imposition
    0.44
    尊重
    0.43
    Act Density 0.035%

    No Known Activations