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

    Neuronpedia

    INDEX
    Explanations

    diseño, estilo, potencial, valores, rol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    1.38
    ED
    1.34
    ing
    1.33
    ed
    1.33
    я
    1.27
    F
    1.23
    L
    1.20
    R
    1.16
    Y
    1.13
    T
    1.13
    POSITIVE LOGITS
     ktorý
    1.04
     وزير
    0.94
     الذين
    0.93
     المجتمع
    0.90
     který
    0.90
    {
    0.89
     الذي
    0.88
     који
    0.87
     pequeño
    0.86
     Desarrollo
    0.86
    Act Density 0.160%

    No Known Activations