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

    Neuronpedia

    INDEX
    Explanations

    nationalities and royalty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    то
    0.49
     aplicações
    0.47
    रु
    0.45
     intervalos
    0.45
     poderia
    0.43
    ravés
    0.43
    ndan
    0.43
     desenvolv
    0.42
     tận
    0.42
    prove
    0.42
    POSITIVE LOGITS
    Emb
    0.50
    I
    0.49
    韩国
    0.49
    Parents
    0.48
     princesses
    0.47
    Spanish
    0.47
    ET
    0.46
    皇家
    0.46
    German
    0.45
     Admiralty
    0.45
    Act Density 0.002%

    No Known Activations