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

    Neuronpedia

    INDEX
    Explanations

    names of organizations and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ceren
    0.38
     cer
    0.35
    Deserialize
    0.35
     விழு
    0.35
    FilesIn
    0.34
     الأح
    0.34
    Potion
    0.34
    沖縄
    0.33
     universes
    0.33
    颛
    0.33
    POSITIVE LOGITS
     প্রেসক্লাবের
    0.39
     ដែល
    0.37
     ([[
    0.36
     जिंदाबाद
    0.36
     ២
    0.35
    way
    0.35
     पो
    0.34
     ({\
    0.34
    bona
    0.34
     這個
    0.34
    Act Density 0.046%

    No Known Activations