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

    Neuronpedia

    INDEX
    Explanations

    military or prohibited actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Realtor
    0.41
     entrer
    0.39
     السي
    0.38
     $<
    0.38
     DECEMBER
    0.38
     Biotech
    0.37
     रियल
    0.37
     മുത
    0.36
     Leisure
    0.36
    మీ
    0.36
    POSITIVE LOGITS
    軍
    0.42
    אל
    0.39
    치
    0.38
    ̀
    0.38
    اعت
    0.35
    Conf
    0.34
    rma
    0.34
    जिंग
    0.34
    ʲ
    0.34
    ｀
    0.34
    Act Density 0.151%

    No Known Activations