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

    Neuronpedia

    INDEX
    Explanations

    Vietnamese and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     чере
    0.42
    вело
    0.38
     longing
    0.37
     hundert
    0.36
     gland
    0.35
     sustained
    0.34
     ஆர
    0.34
    സ്ഥാന
    0.34
    undu
    0.34
    мам
    0.34
    POSITIVE LOGITS
    Cute
    0.42
    美丽的
    0.40
    ส่
    0.40
    Billy
    0.40
    宠物
    0.40
     Billy
    0.39
    RIK
    0.39
    ിയ്
    0.38
    Broadway
    0.38
    itemBackground
    0.38
    Act Density 0.000%

    No Known Activations