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

    Neuronpedia

    INDEX
    Explanations

    not just X, but Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sedangkan
    0.53
     colocar
    0.44
     enquanto
    0.44
     coloque
    0.43
     actualmente
    0.42
     Sedangkan
    0.42
     मीनिंग
    0.42
     whereas
    0.41
     aka
    0.41
     nonché
    0.41
    POSITIVE LOGITS
     merely
    0.75
    只是
    0.61
    普通的
    0.47
    而是
    0.45
     necessarily
    0.45
     simply
    0.44
     mere
    0.44
     actually
    0.43
     usual
    0.40
    仅仅
    0.40
    Act Density 0.028%

    No Known Activations