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

    Neuronpedia

    INDEX
    Explanations

    richest country, War/Terror

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.61
    aient
    0.57
     solicited
    0.57
     paio
    0.57
     Ceci
    0.56
     utilisées
    0.56
     Christus
    0.54
    erde
    0.53
    𝟬
    0.52
     þat
    0.51
    POSITIVE LOGITS
    ਓ
    0.67
    할
    0.64
    का
    0.63
    を取得
    0.63
    órica
    0.62
    を実行
    0.60
    を有
    0.59
    を描
    0.59
    我相信
    0.59
    を設定
    0.58
    Act Density 19.896%

    No Known Activations