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

    Neuronpedia

    INDEX
    Explanations

    targeting infrastructure and civilians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     refugees
    0.51
     Refugees
    0.51
    Airline
    0.47
    Security
    0.46
    security
    0.45
    military
    0.45
     security
    0.44
     Refugee
    0.44
    Expensive
    0.44
     expensive
    0.44
    POSITIVE LOGITS
     disconnecting
    0.44
     مدارس
    0.42
    energie
    0.41
     объекты
    0.40
     roul
    0.40
     cultural
    0.40
     Kultur
    0.40
    కం
    0.39
     क्षतिग्रस्त
    0.39
     purifying
    0.39
    Act Density 0.006%

    No Known Activations