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

    Neuronpedia

    INDEX
    Explanations

    X due to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    because
    1.15
     BECAUSE
    1.12
     porque
    1.10
     because
    1.07
     потому
    1.04
    Porque
    1.00
     omdat
    0.99
    Because
    0.99
    是因为
    0.97
    porque
    0.97
    POSITIVE LOGITS
     sue
    0.61
     do
    0.60
     die
    0.57
     Sue
    0.57
     doe
    0.57
    Sue
    0.57
     dues
    0.52
     ue
    0.51
     dye
    0.50
    do
    0.49
    Act Density 0.048%

    No Known Activations