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

    Neuronpedia

    INDEX
    Explanations

    contrasting clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     military
    0.55
    military
    0.54
     worldwide
    0.51
    worldwide
    0.50
     militares
    0.48
     blackmail
    0.47
     totalitarian
    0.47
     exportation
    0.46
     milit
    0.45
     monopolies
    0.45
    POSITIVE LOGITS
    如果我们
    0.55
    常见
    0.50
    泽
    0.50
    უნქ
    0.50
    殡
    0.50
    یت
    0.50
    时
    0.50
    郓
    0.49
    岛
    0.49
    阐
    0.48
    Act Density 0.001%

    No Known Activations