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

    Neuronpedia

    INDEX
    Explanations

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     products
    0.50
     organizaciones
    0.48
     içeren
    0.48
     websites
    0.44
     compartments
    0.44
     spectrometers
    0.43
     brochures
    0.43
     produits
    0.43
     organi
    0.42
     presentan
    0.42
    POSITIVE LOGITS
    熙
    0.52
    非常
    0.49
     усі
    0.48
    Absolutely
    0.47
    մբ
    0.47
     ผ
    0.45
    贾
    0.45
    됐다
    0.45
     بہترین
    0.45
    勝利
    0.45
    Act Density 0.007%

    No Known Activations