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

    Neuronpedia

    INDEX
    Explanations

    perpetuate biases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discoloration
    0.54
     você
    0.48
     disg
    0.46
     robuste
    0.43
    rijke
    0.43
     допъл
    0.43
     ди
    0.41
     vysok
    0.41
     reflux
    0.41
     மீட்ப
    0.41
    POSITIVE LOGITS
    ᱠ
    0.54
    mselves
    0.48
     Forums
    0.43
    👥
    0.43
    gitian
    0.42
    вніш
    0.41
     Format
    0.41
     হাসি
    0.41
     senate
    0.41
     Sabha
    0.40
    Act Density 0.008%

    No Known Activations