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

    Neuronpedia

    INDEX
    Explanations

    Department of Homeland Security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sharif
    0.40
    밋
    0.39
     বোমা
    0.37
    Render
    0.36
    มีการ
    0.36
     হাইড্রোজেন
    0.36
     Military
    0.36
     Mixtures
    0.36
    Bomb
    0.36
     имеется
    0.36
    POSITIVE LOGITS
     nối
    0.41
    訣
    0.38
     उन्मूलन
    0.37
    ದ್ಧ
    0.37
    口
    0.37
    ensen
    0.37
    形容
    0.37
     ஆதார
    0.37
     falsehood
    0.36
    គ្រ
    0.35
    Act Density 0.000%

    No Known Activations