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

    Neuronpedia

    INDEX
    Explanations

    objects, surfaces, and light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     povinn
    0.47
     responsabil
    0.46
     مؤس
    0.44
    举办
    0.42
     تحقيق
    0.42
     giành
    0.42
     responsabilidad
    0.41
     tanggung
    0.41
     institución
    0.41
     responsabilità
    0.41
    POSITIVE LOGITS
     surfaces
    0.70
     surface
    0.67
     horizontal
    0.54
     vertical
    0.53
     horizontally
    0.51
     unobstructed
    0.51
     geometry
    0.50
     walls
    0.49
     perpendicular
    0.49
     perpendicularly
    0.49
    Act Density 0.184%

    No Known Activations