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

    Neuronpedia

    INDEX
    Explanations

    Transylvania and Pennsylvania

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wells
    0.45
     onion
    0.44
    Сі
    0.43
    Si
    0.42
     Wells
    0.41
    onion
    0.41
     시
    0.41
    aisu
    0.41
     Onion
    0.39
    င်း
    0.39
    POSITIVE LOGITS
    LVANIA
    0.98
    ylvania
    0.96
    ylvan
    0.96
    vania
    0.86
    sylvania
    0.75
    ль
    0.72
    lv
    0.72
    ivan
    0.69
     Sylvia
    0.68
     van
    0.67
    Act Density 0.004%

    No Known Activations