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

    Neuronpedia

    INDEX
    Explanations

    Dragon followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .:
    0.43
     Stef
    0.40
    鸥
    0.40
    парта
    0.38
     орке
    0.38
    이에
    0.36
     ঢাকার
    0.36
    rive
    0.35
     உரிமை
    0.35
    竹
    0.35
    POSITIVE LOGITS
    🐲
    1.23
    🐉
    1.21
     dragon
    1.16
     dragons
    1.10
     Dragon
    1.07
    Dragon
    1.07
     Dragons
    1.02
    龙
    0.95
    dragon
    0.95
    龍
    0.93
    Act Density 0.007%

    No Known Activations