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

    Neuronpedia

    INDEX
    Explanations

    conflict and war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    1.05
    ="
    0.79
     gaseous
    0.78
    ْ
    0.75
     methane
    0.75
     clipboard
    0.70
    ']},
    0.70
    ০০
    0.68
     sabbatical
    0.68
    ม
    0.68
    POSITIVE LOGITS
    િંગ
    0.81
    i
    0.77
    ्स
    0.74
    罢
    0.73
     μεταξύ
    0.73
     battles
    0.71
    នឹង
    0.71
     बिकॉज
    0.69
     μά
    0.68
    ObjectTemp
    0.67
    Act Density 0.285%

    No Known Activations