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

    Neuronpedia

    INDEX
    Explanations

    foreign language detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tượng
    0.46
    განი
    0.42
    そもそも
    0.40
    ඩ්
    0.39
     Его
    0.38
    干
    0.38
     Luh
    0.38
    ["
    0.37
    Dry
    0.37
    երը
    0.37
    POSITIVE LOGITS
    nummer
    0.41
     professionally
    0.40
    ўным
    0.40
    เซีย
    0.40
    dimensioni
    0.37
     alguma
    0.36
    Astr
    0.36
    Commiss
    0.36
    destroyEach
    0.36
     meravigli
    0.36
    Act Density 0.001%

    No Known Activations