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

    Neuronpedia

    INDEX
    Explanations

    SEARCH("query") or pure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bienestar
    0.96
     conexiones
    0.89
     fiestas
    0.88
     elegantes
    0.88
     personajes
    0.87
     solidified
    0.86
    alar
    0.85
     kurulum
    0.85
     herramientas
    0.84
     lavish
    0.84
    POSITIVE LOGITS
    Poly
    0.80
     Poly
    0.80
    Het
    0.76
     Het
    0.71
     разу
    0.71
     Thema
    0.69
    ر
    0.67
    Absolutely
    0.66
    Re
    0.65
    Type
    0.65
    Act Density 0.001%

    No Known Activations