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

    Neuronpedia

    INDEX
    Explanations

    nuclear weapons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Smoothing
    0.43
    smoothing
    0.43
    ígono
    0.43
    شوف
    0.41
    PerPage
    0.41
    粦
    0.40
     प्रधान
    0.40
     ~/
    0.39
    钲
    0.39
    Moving
    0.38
    POSITIVE LOGITS
     nuclear
    0.64
     परमाणु
    0.58
     Nuclear
    0.57
    uclear
    0.56
     ядер
    0.54
     detonation
    0.54
     핵
    0.53
     detonations
    0.52
    nuclear
    0.51
     Hiroshima
    0.50
    Act Density 0.049%

    No Known Activations