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

    Neuronpedia

    INDEX
    Explanations

    defeats the purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ೯
    0.44
     nhưng
    0.44
     işlemler
    0.42
    ub
    0.41
    implementation
    0.40
    obut
    0.40
     প্রচ
    0.40
     исключительно
    0.39
    used
    0.39
     phụ
    0.39
    POSITIVE LOGITS
     Pair
    0.41
     tears
    0.40
     duo
    0.39
     pair
    0.39
     decade
    0.39
    Calle
    0.39
     city
    0.38
     hua
    0.38
     Calif
    0.38
    See
    0.38
    Act Density 0.003%

    No Known Activations