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

    Neuronpedia

    INDEX
    Explanations

    aliens, entities, or spiritual beings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     magic
    0.54
    magic
    0.49
     Magic
    0.47
    魔法
    0.47
    Magic
    0.45
     chaos
    0.44
     জাদু
    0.44
     MAGIC
    0.43
    MAGIC
    0.43
     magical
    0.41
    POSITIVE LOGITS
     messages
    0.82
     mensajes
    0.77
    メッセージ
    0.75
     mensagens
    0.74
     Message
    0.73
     mensaje
    0.72
     message
    0.72
    messages
    0.72
    message
    0.71
     mensagem
    0.70
    Act Density 0.020%

    No Known Activations