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

    Neuronpedia

    INDEX
    Explanations

    Glass, multiplayer, partido, edge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    埛
    0.50
    िता
    0.46
     תו
    0.46
    ی
    0.46
    बॉल
    0.45
    ס
    0.45
    ละ
    0.45
     FE
    0.45
    ༧
    0.45
    ൻ
    0.45
    POSITIVE LOGITS
    0.49
     পশ্চিমবঙ্গের
    0.46
     发布
    0.45
    estre
    0.45
    UMIRE
    0.45
    óng
    0.43
    彦
    0.42
    是不
    0.42
    ající
    0.42
    ávají
    0.42
    Act Density 0.000%

    No Known Activations